The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this paper we provide a review of the challenge from 2008---2012. The paper is intended for two audiences: algorithm designers, researchers who want to see what the state of the art is, as measured by performance on the VOC datasets, along with the limitations and weak points of the current generation of algorithms; and, challenge designers, who want to see what we as organisers have learnt from the process and our recommendations for the organisation of future challenges. To analyse the performance of submitted algorithms on the VOC datasets we introduce a number of novel evaluation methods: a bootstrapping method for determining whether differences in the performance of two algorithms are significant or not; a normalised average precision so that performance can be compared across classes with different proportions of positive instances; a clustering method for visualising the performance across multiple algorithms so that the hard and easy images can be identified; and the use of a joint classifier over the submitted algorithms in order to measure their complementarity and combined performance. We also analyse the community's progress through time using the methods of Hoiem et al. (Proceedings of European Conference on Computer Vision, 2012) to identify the types of occurring errors. We conclude the paper with an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.

/pdf/the-pascal-visual-object-classes-challenge-a-retrospective-28ab0g4997.pdf

The Pascal Visual Object Classes Challenge: A Retrospective

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the \overfeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or $L2$ distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

CNN Features off-the-shelf: an Astounding Baseline for Recognition

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the OverFeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the OverFeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or L2 distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

/pdf/cnn-features-off-the-shelf-an-astounding-baseline-for-3bzk7sak39.pdf

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large- scale visual recognition challenge (ILSVRC2012). The suc- cess of CNNs is attributed to their ability to learn rich mid- level image representations as opposed to hand-designed low-level features used in other image classification meth- ods. Learning CNNs, however, amounts to estimating mil- lions of parameters and requires a very large number of annotated image samples. This property currently prevents application of CNNs to problems with limited training data. In this work we show how image representations learned with CNNs on large-scale annotated datasets can be effi- ciently transferred to other visual recognition tasks with limited amount of training data. We design a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset. We show that despite differences in image statistics and tasks in the two datasets, the transferred rep- resentation leads to significantly improved results for object and action classification, outperforming the current state of the art on Pascal VOC 2007 and 2012 datasets. We also show promising results for object and action localization.

https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Oquab_Learning_and_Transferring_2014_CVPR_paper.pdf

Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved. Some existing approaches focus on minimizing the pixel-wise reconstruction error which results in a high peak signal-to-noise ratio. The enhanced images fail to provide high-frequency details and are perceptually unsatisfying, i.e., they fail to match the quality expected in a photo-realistic image. In this paper, we present Image Enhancement Generative Adversarial Network (IEGAN), a versatile framework capable of inferring photo-realistic natural images for both artifact removal and super-resolution simultaneously. Moreover, we propose a new loss function consisting of a combination of reconstruction loss, feature loss and an edge loss counterpart. The feature loss helps to push the output image to the natural image manifold and the edge loss preserves the sharpness of the output image. The reconstruction loss provides low-level semantic information to the generator regarding the quality of the generated images compared to the original. Our approach has been experimentally proven to recover photo-realistic textures from heavily compressed low-resolution images on public benchmarks and our proposed high-resolution World100 dataset.

/pdf/iegan-multi-purpose-perceptual-quality-image-enhancement-2lh36b7gnj.pdf

IEGAN: Multi-Purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network

Convolutional Neural Networks (CNNs) have shown outstanding performance in visual object tracking. However, most of classification-based tracking methods using CNNs are time-consuming due to expensive computation of complex online fine-tuning and massive feature extractions. Besides, these methods suffer from the problem of over-fitting since the training and testing stages of CNN models are based on the videos from the same domain. Recently, matching-based tracking methods (such as Siamese networks) have shown remarkable speed superiority, while they cannot well address target appearance variations and complex scenes for inherent lack of online adaptability and background information. In this paper, we propose a novel object-adaptive LSTM network, which can effectively exploit sequence dependencies and dynamically adapt to the temporal object variations via constructing an intrinsic model for object appearance and motion. In addition, we develop an efficient strategy for proposal selection, where the densely sampled proposals are firstly pre-evaluated using the fast matching-based method and then the well-selected high-quality proposals are fed to the sequence-specific learning LSTM network. This strategy enables our method to adaptively track an arbitrary object and operate faster than conventional CNN-based classification tracking methods. To the best of our knowledge, this is the first work to apply an LSTM network for classification in visual object tracking. Experimental results on OTB and TC-128 benchmarks show that the proposed method achieves state-of-the-art performance, which exhibits great potentials of recurrent structures for visual object tracking.

/pdf/object-adaptive-lstm-network-for-visual-tracking-3ac7jsuo0h.pdf

Object-Adaptive LSTM Network for Visual Tracking

In this paper, based on the preliminary results on packet transferring in Bluetooth Radio and Baseband layers, we study the packet transferring in the Bluetooth L2CAP layer in AWGN channel. Firstly, we establish two models of packet transferring for L2CAP basic mode and retransmission mode. Then, we obtain the expression for throughput in L2CAP basic mode as a function of channel signal-to-noise ratio (SNR), by 12 different Baseband ACL packets to transfer the L2CAP protocol data units (PDUs). From the simulation result, we propose a packet selection strategy in baseband layer to achieve the maximum throughput for L2CAP basic mode in different channel SNRs. At last, we apply the packet selection strategy to transfer L2CAP PDUs by 3-DH5 baseband packet for L2CAP retransmission mode. Simulation studies are included to illustrate that the proposed packet selection strategy indeed improves the throughput for L2CAP retransmission mode.

Analysis of the packet transferring in L2CAP layer of Bluetooth v2.x+EDR

Loss functions play a crucial role in deep metric learning thus a variety of them have been proposed. Some supervise the learning process by pairwise or tripletwise similarity constraints while others take advantage of structured similarity information among multiple data points. In this work, we approach deep metric learning from a novel perspective. We propose instance cross entropy (ICE) which measures the difference between an estimated instance-level matching distribution and its ground-truth one. ICE has three main appealing properties. Firstly, similar to categorical cross entropy (CCE), ICE has clear probabilistic interpretation and exploits structured semantic similarity information for learning supervision. Secondly, ICE is scalable to infinite training data as it learns on mini-batches iteratively and is independent of the training set size. Thirdly, motivated by our relative weight analysis, seamless sample reweighting is incorporated. It rescales samples' gradients to control the differentiation degree over training examples instead of truncating them by sample mining. In addition to its simplicity and intuitiveness, extensive experiments on three real-world benchmarks demonstrate the superiority of ICE.

/pdf/instance-cross-entropy-for-deep-metric-learning-43wk05z5mt.pdf

Instance Cross Entropy for Deep Metric Learning

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. Consequently, some useful examples are ignored and the structure is less informative. To address this, we propose to build a set-based similarity structure by exploiting all instances in the gallery. The learning setting can be interpreted as few-shot retrieval: given a mini-batch, every example is iteratively used as a query, and the rest ones compose the gallery to search, i.e., the support set in few-shot setting. The rest examples are split into a positive set and a negative set. For every mini-batch, the learning objective of ranked list loss is to make the query closer to the positive set than to the negative set by a margin. Second, previous methods aim to pull positive pairs as close as possible in the embedding space. As a result, the intraclass data distribution tends to be extremely compressed. In contrast, we propose to learn a hypersphere for each class in order to preserve useful similarity structure inside it, which functions as regularisation. Extensive experiments demonstrate the superiority of our proposal by comparing with the state-of-the-art methods.

Yang Hua

Papers

IEGAN: Multi-Purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network

Object-Adaptive LSTM Network for Visual Tracking

Analysis of the packet transferring in L2CAP layer of Bluetooth v2.x+EDR

Instance Cross Entropy for Deep Metric Learning

Ranked List Loss for Deep Metric Learning