ImageNet Large Scale Visual Recognition Challenge
01 Dec 2015-International Journal of Computer Vision (Springer Netherlands)-Vol. 115, Iss: 3, pp 211-252
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Abstract: 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.
Citations
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
Book•
[...]
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
38,208 citations
Proceedings Article•
06 Jul 2015TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Abstract: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.
30,843 citations
21 Jul 2017
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Abstract: Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one between each layer and its subsequent layer—our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.
27,821 citations
References
More filters
16 Jun 2012
TL;DR: This work shows how to construct normalized “multi-attribute spaces” from raw classifier outputs, using techniques based on the statistical Extreme Value Theory, and shows that perceptual similarity of search results increases by using contextual attributes.
Abstract: Recent work has shown that visual attributes are a powerful approach for applications such as recognition, image description and retrieval However, fusing multiple attribute scores — as required during multi-attribute queries or similarity searches — presents a significant challenge Scores from different attribute classifiers cannot be combined in a simple way; the same score for different attributes can mean different things In this work, we show how to construct normalized “multi-attribute spaces” from raw classifier outputs, using techniques based on the statistical Extreme Value Theory Our method calibrates each raw score to a probability that the given attribute is present in the image We describe how these probabilities can be fused in a simple way to perform more accurate multiattribute searches, as well as enable attribute-based similarity searches A significant advantage of our approach is that the normalization is done after-the-fact, requiring neither modification to the attribute classification system nor ground truth attribute annotations We demonstrate results on a large data set of nearly 2 million face images and show significant improvements over prior work We also show that perceptual similarity of search results increases by using contextual attributes
208 citations
26 Apr 2014
TL;DR: An algorithm that exploits correlation, hierarchy, and sparsity of the label distribution is proposed that results in up to 6x reduction in human computation time compared to the naive method of querying a human annotator for the presence of every object in every image.
Abstract: We study strategies for scalable multi-label annotation, or for efficiently acquiring multiple labels from humans for a collection of items. We propose an algorithm that exploits correlation, hierarchy, and sparsity of the label distribution. A case study of labeling 200 objects using 20,000 images demonstrates the effectiveness of our approach. The algorithm results in up to 6x reduction in human computation time compared to the naive method of querying a human annotator for the presence of every object in every image.
162 citations
07 Oct 2012
TL;DR: A general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models, by making use of properties of the Fourier transform and of clever implementation strategies.
Abstract: We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models The main bottleneck of many of those systems is the computational cost of the convolutions between the multiple rescalings of the image to process, and the linear filters We make use of properties of the Fourier transform and of clever implementation strategies to obtain a speedup factor proportional to the filters' sizes The gain in performance is demonstrated on the well known Pascal VOC benchmark, where we accelerate the speed of said convolutions by an order of magnitude
160 citations
Posted Content•
TL;DR: A set of models with large diversity are obtained, which significantly improves the effectiveness of modeling averaging, and improves the mean averaged precision obtained by RCNN, which is the state of the art of object detection, from31% to 45%.
Abstract: In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (defpooling) layer models the deformation of object parts with geometric constraint and penalty. With the proposed multistage training strategy, multiple classifiers are jointly optimized to process samples at different difficulty levels. A ne w pre-training strategy is proposed to learn feature represe ntations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of modeling averaging. The proposed approach ranked #2 in ILSVRC 2014. It improves the mean averaged precision obtained by RCNN, which is the stateof-the-art of object detection, from31% to 45%. Detailed component-wise analysis is also provided through extensiv e experimental evaluation.
155 citations
Posted Content•
02 Jun 2013
TL;DR: This paper proposes to train all layers of the deep networks by backpropagating gradients through the top level SVM, learning features of all layers, and demonstrates a small but consistent advantage of replacing softmax layer with a linear support vector machine.
Abstract: Recently, fully-connected and convolutional neural networks have been trained to reach state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics data. For classification tasks, much of these “deep learning” models employ the softmax activation functions to learn output labels in 1-of-K format. In this paper, we demonstrate a small but consistent advantage of replacing softmax layer with a linear support vector machine. Learning minimizes a margin-based loss instead of the cross-entropy loss. In almost all of the previous works, hidden representation of deep networks are first learned using supervised or unsupervised techniques, and then are fed into SVMs as inputs. In contrast to those models, we are proposing to train all layers of the deep networks by backpropagating gradients through the top level SVM, learning features of all layers. Our experiments show that simply replacing softmax with linear SVMs gives significant gains on datasets MNIST, CIFAR-10, and the ICML 2013 Representation Learning Workshop’s face expression recognition challenge.
153 citations