Going deeper with convolutions
07 Jun 2015-pp 1-9
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
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
Posted Content•
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
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---8x deeper than VGG nets 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 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
44,703 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
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
33,301 citations
References
More filters
Proceedings Article•
IBM1
TL;DR: A new algorithm is presented that intuitively captures the primary goal of reducing the misclassification error and achieves good accuracy, small trees, and fast execution times in the MDL pruning algorithm.
Abstract: This paper explores the application of the Minimum Description Length principle for pruning decision trees. We present a new algorithm that intuitively captures the primary goal of reducing the misclassification error. An experimental comparison is presented with three other pruning algorithms. The results show that the MDL pruning algorithm achieves good accuracy, small trees, and fast execution times.
237 citations
TL;DR: A new model for estimating optical flow based on the motion of planar regions plus local deformations which exploits the strong constraints of parametric approaches while retaining the adaptive nature of regularization approaches.
Abstract: This paper presents a new model for estimating optical flow based on the motion of planar regions plus local deformations. The approach exploits brightness information to organize and constrain the interpretation of the motion by using segmented regions of piecewise smooth brightness to hypothesize planar regions in the scene. Parametric flow models are estimated in these regions in a two step process which first computes a coarse fit and then estimates the appropriate parametrization of the motion of the region. The initial fit is refined using a generalization of the standard area-based regression approaches. Since the assumption of planarity is likely to be violated, we allow local deformations from the planar assumption in the same spirit as physically-based approaches which model shape using coarse parametric models plus local deformations. This parametric plus deformation model exploits the strong constraints of parametric approaches while retaining the adaptive nature of regularization approaches. Experimental results on a variety of images model produces accurate flow estimates while the incorporation of brightness segmentation boundaries.
237 citations
10 Dec 2012
TL;DR: This work exploits multiple representations for the same set of instances within a clustering framework in terms of given kernel matrices and a weighted combination of the kernels is learned in parallel to the partitioning.
Abstract: Exploiting multiple representations, or views, for the same set of instances within a clustering framework is a popular practice for boosting clustering accuracy. However, some of the available sources may be misleading (due to noise, errors in measurement etc.) in revealing the true structure of the data, thus, their inclusion in the clustering process may have negative influence. This aspect seems to be overlooked in the multi-view literature where all representations are equally considered. In this work, views are expressed in terms of given kernel matrices and a weighted combination of the kernels is learned in parallel to the partitioning. Weights assigned to kernels are indicative of the quality of the corresponding views' information. Additionally, the combination scheme incorporates a parameter that controls the admissible sparsity of the weights to avoid extremes and tailor them to the data. Two efficient iterative algorithms are proposed that alternate between updating the view weights and recomputing the clusters to optimize the intra-cluster variance from different perspectives. The conducted experiments reveal the effectiveness of our methodology compared to other multi-view methods.
233 citations
23 Jun 2014
TL;DR: It is shown that better action recognition using skeletal features can be achieved by replacing gaussian mixture models by deep neural networks that contain many layers of features to predict probability distributions over states of hidden Markov models.
Abstract: Over the last few years, with the immense popularity of the Kinect, there has been renewed interest in developing methods for human gesture and action recognition from 3D skeletal data. A number of approaches have been proposed to extract representative features from 3D skeletal data, most commonly hard wired geometric or bio-inspired shape context features. We propose a hierarchial dynamic framework that first extracts high level skeletal joints features and then uses the learned representation for estimating emission probability to infer action sequences. Currently gaussian mixture models are the dominant technique for modeling the emission distribution of hidden Markov models. We show that better action recognition using skeletal features can be achieved by replacing gaussian mixture models by deep neural networks that contain many layers of features to predict probability distributions over states of hidden Markov models. The framework can be easily extended to include a ergodic state to segment and recognize actions simultaneously.
224 citations
17 Sep 2007
TL;DR: It is shown that the co- training process can succeed even without two views, given that the two learners have large difference, which explains the success of some co-training style algorithms that do not require two views.
Abstract: Co-training is a semi-supervised learning paradigm which trains two learners respectively from two different views and lets the learners label some unlabeled examples for each other. In this paper, we present a new PAC analysis on co-training style algorithms. We show that the co-training process can succeed even without two views, given that the two learners have large difference, which explains the success of some co-training style algorithms that do not require two views. Moreover, we theoretically explain that why the co-training process could not improve the performance further after a number of rounds, and present a rough estimation on the appropriate round to terminate co-training to avoid some wasteful learning rounds.
223 citations