Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

/pdf/rich-feature-hierarchies-for-accurate-object-detection-and-22fvjlggyg.pdf

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1（PfPMP1）与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用，在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员，通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

疟原虫var基因转换速率变化导致抗原变异[英]／Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.

/pdf/multiresolution-gray-scale-and-rotation-invariant-texture-1b1y2fta4g.pdf

Multiresolution gray-scale and rotation invariant texture classification with local binary patterns

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at this http URL.

Rich feature hierarchies for accurate object detection and semantic segmentation

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

More and more researchers focus their studies on multiview activity recognition, because a fixed view could not provide enough information for recognition. In this paper, we use multi-view features to recognize six kinds of gymnastic activities. Firstly, shape-based features are extracted from two orthogonal cameras in the form of R transform. Then a multi-view approach based on Fused HMM is proposed to combine different features for similar gymnastic activity recognition. Compared with other activity models, our method achieves better performance even in the case of frame loss.

/pdf/multi-view-gymnastic-activity-recognition-with-fused-hmm-2j57wezxql.pdf

Multi-view gymnastic activity recognition with fused HMM

In this paper, a feature-level fusion based approach is proposed for blind image steganalysis. We choose three types of typical higher-order statistics as the candidate features for fusion and make use of the Boosting Feature Selection (BFS) algorithm as the fusion tool to select a subset of these candidate features as the new fusion feature vector for blind image steganalysis. Support vector machines are then used as the classifier. Experimental results show that the fusion based approach increases the blind detection accuracy and also provides a good generality by identifying an untrained stego-algorithm. Moreover, we evaluate the performance of our candidate features for fusion by making some analysis of the components of the fusion feature vector in our experiments.

Fusion Based Blind Image Steganalysis by Boosting Feature Selection

For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data. In this paper, we proposed an approach, named Relation Discovery based Slow Feature Analysis (ReD-SFA), for feature learning and graph construction simultaneously. Given an initial graph with only a few nearest but most reliable pairwise relations, new reliable relations are discovered by an assumption of reliability preservation, i.e., the reliable relations will preserve their reliabilities in the learnt projection subspace. We formulate the idea as a cross entropy (CE) minimization problem to reduce the discrepancy between two Bernoulli distributions parameterized by the updated distances and the existing relation graph respectively. Furthermore, to overcome the imbalanced distribution of samples, a Boosting-like strategy is proposed to balance the discovered relations over all clusters. To evaluate the proposed method, extensive experiments are performed with various trajectory clustering tasks, including motion segmentation, time series clustering and crowd detection. The results demonstrate that ReDSFA can discover reliable intra-cluster relations with high precision, and competitive clustering performance can be achieved in comparison with state-of-the-art.

/pdf/red-sfa-relation-discovery-based-slow-feature-analysis-for-42vemyad73.pdf

ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering

Single image deraining refers to the process of restoring the clean background scene from a rainy image. Current approaches have resorted to deep learning techniques to remove rain from a single image by leveraging some prior information. However, due to the various appearances of rain streaks and accumulation, it is difficult to separate rain and background information in the embedding space, which results in inaccurate deraining. To address this issue, this paper proposes a selective wavelet attention learning method by learning a series of wavelet attention maps to guide the separation of rain and background information in both spatial and frequency domains. The key aspect of our method is utilizing wavelet transform to learn the content and structure of rainy features because the high-frequency features are more sensitive to rain degradations, whereas the low-frequency features preserve more of the background content. To begin with, we develop a selective wavelet attention encoder–decoder network to learn wavelet attention maps guiding the separation of rainy and background features at multiple scales. Meanwhile, we introduce wavelet pooling and unpooling to the encoder–decoder network, which shows superiority in learning increasingly abstract representations while preserving the background details. In addition, we propose latent alignment learning to supervise the background features as well as augment the training data to further improve the accuracy of deraining. Finally, we employ a hierarchical discriminator network based on selective wavelet attention to adversarially improve the visual fidelity of the generated results both globally and locally. Extensive experiments on synthetic and real datasets demonstrate that the proposed approach achieves more appealing results both quantitatively and qualitatively than the recent state-of-the-art methods.

Selective Wavelet Attention Learning for Single Image Deraining

Scale-sensitive object detection remains a challenging task, where most of the existing methods not learn it explicitly and not robust to scale variance. In addition, the most existing methods are less efficient during training or slow during inference, which are not friendly to real-time application. In this paper, we propose a practical object detection with scale-sensitive network.Our method first predicts a global continuous scale ,which shared by all position, for each convolution filter of each network stage. To effectively learn the scale, we average the spatial features and distill the scale from channels. For fast-deployment, we propose a scale decomposition method that transfers the robust fractional scale into combinations of fixed integral scales for each convolution filter, which exploit the dilated convolution. We demonstrate it on one-stage and two-stage algorithm under almost different configure. For practical application, training of our method is of efficiency and simplicity which gets rid of complex data sampling or optimize strategy. During testing, the proposed method requires no extra operation and is very friendly to hardware acceleration like TensorRT and TVM.On the COCO test-dev, our model could achieve a 41.5mAP on one-stage detector and 42.1 mAP on two-stage detectors based on ResNet-101, outperforming baselines by 2.4 and 2.1 respectively without extra FLOPS.

/pdf/pod-practical-object-detection-with-scale-sensitive-network-mo9f3nzmbj.pdf

Tieniu Tan

Papers

Multi-view gymnastic activity recognition with fused HMM

Fusion Based Blind Image Steganalysis by Boosting Feature Selection

ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering

Selective Wavelet Attention Learning for Single Image Deraining

POD: Practical Object Detection With Scale-Sensitive Network