Showing papers on "Feature vector published in 2018"

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Abstract: Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

Abstract: The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 10^{4} data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks.

Abstract: Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.

Implementation of machine-learning classification in remote sensing: an applied review

Abstract: Machine learning offers the potential for effective and efficient classification of remotely sensed imagery. The strengths of machine learning include the capacity to handle data of high dimensionality and to map classes with very complex characteristics. Nevertheless, implementing a machine-learning classification is not straightforward, and the literature provides conflicting advice regarding many key issues. This article therefore provides an overview of machine learning from an applied perspective. We focus on the relatively mature methods of support vector machines, single decision trees (DTs), Random Forests, boosted DTs, artificial neural networks, and k-nearest neighbours (k-NN). Issues considered include the choice of algorithm, training data requirements, user-defined parameter selection and optimization, feature space impacts and reduction, and computational costs. We illustrate these issues through applying machine-learning classification to two publically available remotely sensed dat...

SO-Net: Self-Organizing Network for Point Cloud Analysis

Abstract: This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture. Our code is available at the project website.1

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Abstract: We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds. SGPN uses a single network to predict point grouping proposals and a corresponding semantic class for each proposal, from which we can directly extract instance segmentation results. Important to the effectiveness of SGPN is its novel representation of 3D instance segmentation results in the form of a similarity matrix that indicates the similarity between each pair of points in embedded feature space, thus producing an accurate grouping proposal for each point. Experimental results on various 3D scenes show the effectiveness of our method on 3D instance segmentation, and we also evaluate the capability of SGPN to improve 3D object detection and semantic segmentation results. We also demonstrate its flexibility by seamlessly incorporating 2D CNN features into the framework to boost performance.

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Abstract: Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there are two significant challenges: (1) degenerated feature transformation, which means that distribution alignment is often performed in the original feature space, where feature distortions are hard to overcome. On the other hand, subspace learning is not sufficient to reduce the distribution divergence. (2) unevaluated distribution alignment, which means that existing distribution alignment methods only align the marginal and conditional distributions with equal importance, while they fail to evaluate the different importance of these two distributions in real applications. In this paper, we propose a Manifold Embedded Distribution Alignment (MEDA) approach to address these challenges. MEDA learns a domain-invariant classifier in Grassmann manifold with structural risk minimization, while performing dynamic distribution alignment to quantitatively account for the relative importance of marginal and conditional distributions. To the best of our knowledge, MEDA is the first attempt to perform dynamic distribution alignment for manifold domain adaptation. Extensive experiments demonstrate that MEDA shows significant improvements in classification accuracy compared to state-of-the-art traditional and deep methods.

Unsupervised Person Re-identification: Clustering and Fine-tuning

Abstract: The superiority of deeply learned pedestrian representations has been reported in very recent literature of person re-identification (re-ID). In this article, we consider the more pragmatic issue of learning a deep feature with no or only a few labels. We propose a progressive unsupervised learning (PUL) method to transfer pretrained deep representations to unseen domains. Our method is easy to implement and can be viewed as an effective baseline for unsupervised re-ID feature learning. Specifically, PUL iterates between (1) pedestrian clustering and (2) fine-tuning of the convolutional neural network (CNN) to improve the initialization model trained on the irrelevant labeled dataset. Since the clustering results can be very noisy, we add a selection operation between the clustering and fine-tuning. At the beginning, when the model is weak, CNN is fine-tuned on a small amount of reliable examples that locate near to cluster centroids in the feature space. As the model becomes stronger, in subsequent iterations, more images are being adaptively selected as CNN training samples. Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence. This process is naturally formulated as self-paced learning. We then point out promising directions that may lead to further improvement. Extensive experiments on three large-scale re-ID datasets demonstrate that PUL outputs discriminative features that improve the re-ID accuracy. Our code has been released at https://github.com/hehefan/Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning.

cGANs with Projection Discriminator

Abstract: We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the current state-of-the-art result, and we achieved this with a single pair of a discriminator and a generator. We were also able to extend the application to super-resolution and succeeded in producing highly discriminative super-resolution images. This new structure also enabled high quality category transformation based on parametric functional transformation of conditional batch normalization layers in the generator.

Disentangled Person Image Generation

Abstract: Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor, respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on the Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task1.

Supervised learning with quantum enhanced feature spaces

Abstract: Machine learning and quantum computing are two technologies each with the potential for altering how computation is performed to address previously untenable problems. Kernel methods for machine learning are ubiquitous for pattern recognition, with support vector machines (SVMs) being the most well-known method for classification problems. However, there are limitations to the successful solution to such problems when the feature space becomes large, and the kernel functions become computationally expensive to estimate. A core element to computational speed-ups afforded by quantum algorithms is the exploitation of an exponentially large quantum state space through controllable entanglement and interference. Here, we propose and experimentally implement two novel methods on a superconducting processor. Both methods represent the feature space of a classification problem by a quantum state, taking advantage of the large dimensionality of quantum Hilbert space to obtain an enhanced solution. One method, the quantum variational classifier builds on [1,2] and operates through using a variational quantum circuit to classify a training set in direct analogy to conventional SVMs. In the second, a quantum kernel estimator, we estimate the kernel function and optimize the classifier directly. The two methods present a new class of tools for exploring the applications of noisy intermediate scale quantum computers [3] to machine learning.

PU-Net: Point Cloud Upsampling Network

Abstract: Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of features, which are then reconstructed to an upsampled point set. Our network is applied at a patch-level, with a joint loss function that encourages the upsampled points to remain on the underlying surface with a uniform distribution. We conduct various experiments using synthesis and scan data to evaluate our method and demonstrate its superiority over some baseline methods and an optimization-based method. Results show that our upsampled points have better uniformity and are located closer to the underlying surfaces.

A strategy to apply machine learning to small datasets in materials science

Abstract: There is growing interest in applying machine learning techniques in the research of materials science. However, although it is recognized that materials datasets are typically smaller and sometimes more diverse compared to other fields, the influence of availability of materials data on training machine learning models has not yet been studied, which prevents the possibility to establish accurate predictive rules using small materials datasets. Here we analyzed the fundamental interplay between the availability of materials data and the predictive capability of machine learning models. Instead of affecting the model precision directly, the effect of data size is mediated by the degree of freedom (DoF) of model, resulting in the phenomenon of association between precision and DoF. The appearance of precision–DoF association signals the issue of underfitting and is characterized by large bias of prediction, which consequently restricts the accurate prediction in unknown domains. We proposed to incorporate the crude estimation of property in the feature space to establish ML models using small sized materials data, which increases the accuracy of prediction without the cost of higher DoF. In three case studies of predicting the band gap of binary semiconductors, lattice thermal conductivity, and elastic properties of zeolites, the integration of crude estimation effectively boosted the predictive capability of machine learning models to state-of-art levels, demonstrating the generality of the proposed strategy to construct accurate machine learning models using small materials dataset. Machine learning can be useful for materials prediction if crude estimations of the outcome are integrated in the code. Machine learning has been attracting tremendous attention lately due to its predictive power; evidence suggests it is directly proportional to the size of the available datasets. Machine learning can be useful in predicting new materials and novel properties, but materials sets tend to be smaller and more diverse than other fields. Ying Zhang and Chen Ling from the Toyota Research Institute of North America report that these small datasets affect the freedom of the algorithms and thus limit their predictive capabilities. In order to counterbalance the effect, they suggest introducing in the code crude estimations of the targeted property, obtained by other means.

Recurrent Slice Networks for 3D Segmentation of Point Clouds

Abstract: Point clouds are an efficient data format for 3D data. However, existing 3D segmentation methods for point clouds either do not model local dependencies [21] or require added computations [14, 23]. This work presents a novel 3D segmentation framework, RSNet1, to efficiently model local structures in point clouds. The key component of the RSNet is a lightweight local dependency module. It is a combination of a novel slice pooling layer, Recurrent Neural Network (RNN) layers, and a slice unpooling layer. The slice pooling layer is designed to project features of unordered points onto an ordered sequence of feature vectors so that traditional end-to-end learning algorithms (RNNs) can be applied. The performance of RSNet is validated by comprehensive experiments on the S3DIS[1], ScanNet[3], and ShapeNet [34] datasets. In its simplest form, RSNets surpass all previous state-of-the-art methods on these benchmarks. And comparisons against previous state-of-the-art methods [21, 23] demonstrate the efficiency of RSNets.

Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models

Abstract: Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that embed image-text pairs as single feature vectors in a common representational space, we propose to incorporate generative processes into the cross-modal feature embedding, through which we are able to learn not only the global abstract features but also the local grounded features. Extensive experiments show that our framework can well match images and sentences with complex content, and achieve the state-of-the-art cross-modal retrieval results on MSCOCO dataset.

SO-Net: Self-Organizing Network for Point Cloud Analysis

Abstract: This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture. Our code is available at the project website. this https URL

A DIRT-T Approach to Unsupervised Domain Adaptation

Abstract: Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempts to induce a feature extractor that matches the source and target feature distributions in some feature space. However, domain adversarial training faces two critical limitations: 1) if the feature extraction function has high-capacity, then feature distribution matching is a weak constraint, 2) in non-conservative domain adaptation (where no single classifier can perform well in both the source and target domains), training the model to do well on the source domain hurts performance on the target domain. In this paper, we address these issues through the lens of the cluster assumption, i.e., decision boundaries should not cross high-density data regions. We propose two novel and related models: 1) the Virtual Adversarial Domain Adaptation (VADA) model, which combines domain adversarial training with a penalty term that punishes the violation the cluster assumption; 2) the Decision-boundary Iterative Refinement Training with a Teacher (DIRT-T) model, which takes the VADA model as initialization and employs natural gradient steps to further minimize the cluster assumption violation. Extensive empirical results demonstrate that the combination of these two models significantly improve the state-of-the-art performance on the digit, traffic sign, and Wi-Fi recognition domain adaptation benchmarks.

A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images

Abstract: We propose an unsupervised deep convolutional coupling network for change detection based on two heterogeneous images acquired by optical sensors and radars on different dates. Most existing change detection methods are based on homogeneous images. Due to the complementary properties of optical and radar sensors, there is an increasing interest in change detection based on heterogeneous images. The proposed network is symmetric with each side consisting of one convolutional layer and several coupling layers. The two input images connected with the two sides of the network, respectively, are transformed into a feature space where their feature representations become more consistent. In this feature space, the different map is calculated, which then leads to the ultimate detection map by applying a thresholding algorithm. The network parameters are learned by optimizing a coupling function. The learning process is unsupervised, which is different from most existing change detection methods based on heterogeneous images. Experimental results on both homogenous and heterogeneous images demonstrate the promising performance of the proposed network compared with several existing approaches.

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification

Abstract: Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intrasequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a decorrelation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods.

A novel embedding model for knowledge base completion based on convolutional neural network

Abstract: In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3-column matrix where each column vector represents a triple element. This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature vector representing the input triple. The feature vector is multiplied with a weight vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237.

Learning Deep Representations with Probabilistic Knowledge Transfer

Abstract: Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper we propose a novel probabilistic knowledge transfer method that works by matching the probability distribution of the data in the feature space instead of their actual representation. Apart from outperforming existing KT techniques, the proposed method allows for overcoming several of their limitations providing new insight into KT as well as novel KT applications, ranging from KT from handcrafted feature extractors to cross-modal KT from the textual modality into the representation extracted from the visual modality of the data.

Deep Cosine Metric Learning for Person Re-identification

Abstract: Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.

Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning

Abstract: Effective intelligent fault diagnosis has long been a research focus on the condition monitoring of rotary machinery systems. Traditionally, time-domain vibration-based fault diagnosis has some deficiencies, such as complex computation of feature vectors, excessive dependence on prior knowledge and diagnostic expertise, and limited capacity for learning complex relationships in fault signals. Furthermore, following the increase in condition data, how to promptly process the massive fault data and automatically provide accurate diagnosis has become an urgent need to solve. Inspired by the idea of compressed sensing and deep learning, a novel intelligent diagnosis method is proposed for fault identification of rotating machines. In this paper, a nonlinear projection is applied to achieve the compressed acquisition, which not only reduces the amount of measured data that contained all the information of faults but also realizes the automatic feature extraction in transform domain. For exploring the discrimination hidden in the acquired data, a stacked sparse autoencoders-based deep neural network is established and performed with an unsupervised learning procedure followed by a supervised fine-tuning process. We studied the significance of compressed acquisition and provided the effects of key factors and comparison with traditional methods. The effectiveness of the proposed method is validated using data sets from rolling element bearings and the analysis shows that it is able to obtain high diagnotic accuracies and is superior to the existing methods. The proposed method reduces the need of human labor and expertise and provides new strategy to handle the massive data more easily.

ACPred-FL: a sequence-based predictor using effective feature representation to improve the prediction of anti-cancer peptides.

Abstract: Motivation Anti-cancer peptides (ACPs) have recently emerged as promising therapeutic agents for cancer treatment. Due to the avalanche of protein sequence data in the post-genomic era, there is an urgent need to develop automated computational methods to enable fast and accurate identification of novel ACPs within the vast number of candidate proteins and peptides. Results To address this, we propose a novel predictor named Anti-Cancer peptide Predictor with Feature representation Learning (ACPred-FL) for accurate prediction of ACPs based on sequence information. More specifically, we develop an effective feature representation learning model, with which we can extract and learn a set of informative features from a pool of support vector machine-based models trained using sequence-based feature descriptors. By doing so, the class label information of data samples is fully utilized. To improve the feature representation, we further employ a two-step feature selection technique, resulting in a most informative five-dimensional feature vector for the final peptide representation. Experimental results show that such five features provide the most discriminative power for identifying ACPs than currently available feature descriptors, highlighting the effectiveness of the proposed feature representation learning approach. The developed ACPred-FL method significantly outperforms state-of-the-art methods. Availability and implementation The web-server of ACPred-FL is available at http://server.malab.cn/ACPred-FL. Supplementary information Supplementary data are available at Bioinformatics online.

The Extreme Value Machine

Abstract: It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a human operator, allowing them to be incorporated into the recognition function—ideally under an efficient incremental update mechanism. While good algorithms that assume inputs from a fixed set of classes exist, e.g. , artificial neural networks and kernel machines, it is not immediately obvious how to extend them to perform incremental learning in the presence of unknown query classes. Existing algorithms take little to no distributional information into account when learning recognition functions and lack a strong theoretical foundation. We address this gap by formulating a novel, theoretically sound classifier—the Extreme Value Machine (EVM). The EVM has a well-grounded interpretation derived from statistical Extreme Value Theory (EVT), and is the first classifier to be able to perform nonlinear kernel-free variable bandwidth incremental learning. Compared to other classifiers in the same deep network derived feature space, the EVM is accurate and efficient on an established benchmark partition of the ImageNet dataset.

3D-CODED: 3D Correspondences by Deep Deformation

Abstract: We present a new deep learning approach for matching deformable shapes by introducing Shape Deformation Networks which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface. By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template. We show that these correspondences can be improved by an additional step which improves the shape feature by minimizing the Chamfer distance between the input and transformed template. We demonstrate that our simple approach improves on state-of-the-art results on the difficult FAUST-inter challenge, with an average correspondence error of 2.88 cm. We show, on the TOSCA dataset, that our method is robust to many types of perturbations, and generalizes to non-human shapes. This robustness allows it to perform well on real unclean, meshes from the SCAPE dataset.

An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition

Abstract: Video semantic recognition usually suffers from the curse of dimensionality and the absence of enough high-quality labeled instances, thus semisupervised feature selection gains increasing attentions for its efficiency and comprehensibility. Most of the previous methods assume that videos with close distance (neighbors) have similar labels and characterize the intrinsic local structure through a predetermined graph of both labeled and unlabeled data. However, besides the parameter tuning problem underlying the construction of the graph, the affinity measurement in the original feature space usually suffers from the curse of dimensionality. Additionally, the predetermined graph separates itself from the procedure of feature selection, which might lead to downgraded performance for video semantic recognition. In this paper, we exploit a novel semisupervised feature selection method from a new perspective. The primary assumption underlying our model is that the instances with similar labels should have a larger probability of being neighbors. Instead of using a predetermined similarity graph, we incorporate the exploration of the local structure into the procedure of joint feature selection so as to learn the optimal graph simultaneously. Moreover, an adaptive loss function is exploited to measure the label fitness, which significantly enhances model’s robustness to videos with a small or substantial loss. We propose an efficient alternating optimization algorithm to solve the proposed challenging problem, together with analyses on its convergence and computational complexity in theory. Finally, extensive experimental results on benchmark datasets illustrate the effectiveness and superiority of the proposed approach on video semantic recognition related tasks.

Viewpoint-Aware Attentive Multi-view Inference for Vehicle Re-identification

Abstract: Vehicle re-identification (re-ID) has the huge potential to contribute to the intelligent video surveillance. However, it suffers from challenges that different vehicle identities with a similar appearance have little inter-instance discrepancy while one vehicle usually has large intra-instance differences under viewpoint and illumination variations. Previous methods address vehicle re-ID by simply using visual features from originally captured views and usually exploit the spatial-temporal information of the vehicles to refine the results. In this paper, we propose a Viewpoint-aware Attentive Multi-view Inference (VAMI) model that only requires visual information to solve the multi-view vehicle reID problem. Given vehicle images of arbitrary viewpoints, the VAMI extracts the single-view feature for each input image and aims to transform the features into a global multiview feature representation so that pairwise distance metric learning can be better optimized in such a viewpointinvariant feature space. The VAMI adopts a viewpoint-aware attention model to select core regions at different viewpoints and implement effective multi-view feature inference by an adversarial training architecture. Extensive experiments validate the effectiveness of each proposed component and illustrate that our approach achieves consistent improvements over state-of-the-art vehicle re-ID methods on two public datasets: VeRi and VehicleID.