Results 1 - 10
of
252
Imagenet classification with deep convolutional neural networks.
- In Advances in the Neural Information Processing System,
, 2012
"... 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% which is considerably better than the pr ..."
Abstract
-
Cited by 1010 (11 self)
- Add to MetaCart
(Show Context)
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% 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.
Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition
- IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
, 2012
"... We propose a novel context-dependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pretrained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to pr ..."
Abstract
-
Cited by 254 (50 self)
- Add to MetaCart
We propose a novel context-dependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pretrained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8 % and 9.2 % (or relative error reduction of 16.0 % and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively.
Learning mid-level features for recognition
, 2010
"... Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of intermediate complexity. This process can often be broken down into two steps: (1) a coding step, which performs a pointwise tra ..."
Abstract
-
Cited by 228 (13 self)
- Add to MetaCart
(Show Context)
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of intermediate complexity. This process can often be broken down into two steps: (1) a coding step, which performs a pointwise transformation of the descriptors into a representation better adapted to the task, and (2) a pooling step, which summarizes the coded features over larger neighborhoods. Several combinations of coding and pooling schemes have been proposed in the literature. The goal of this paper is threefold. We seek to establish the relative importance of each step of mid-level feature extraction through a comprehensive cross evaluation of several types of coding modules (hard and soft vector quantization, sparse coding) and pooling schemes (by taking the average, or the maximum), which obtains state-of-the-art performance or better on several recognition benchmarks. We show how to improve the best performing coding scheme by learning a supervised discriminative dictionary for sparse coding. We provide theoretical and empirical insight into the remarkable performance of max pooling. By teasing apart components shared by modern mid-level feature extractors, our approach aims to facilitate the design of better recognition architectures.
An Analysis of Single-Layer Networks in Unsupervised Feature Learning
"... A great deal of research has focused on algorithms for learning features from unlabeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR by employing increasingly complex unsupervised learning algorithms and deep models. In this paper, however, we show that several ..."
Abstract
-
Cited by 223 (19 self)
- Add to MetaCart
(Show Context)
A great deal of research has focused on algorithms for learning features from unlabeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR by employing increasingly complex unsupervised learning algorithms and deep models. In this paper, however, we show that several very simple factors, such as the number of hidden nodes in the model, may be as important to achieving high performance as the choice of learning algorithm or the depth of the model. Specifically, we will apply several off-the-shelf feature learning algorithms (sparse auto-encoders, sparse RBMs and K-means clustering, Gaussian mixtures) to NORB and CIFAR datasets using only single-layer networks. We then present a detailed analysis of the effect of changes in the model setup: the receptive field size, number of hidden nodes (features), the step-size (“stride”) between extracted features, and the effect of whitening. Our results show that large numbers of hidden nodes and dense feature extraction are as critical to achieving high performance as the choice of algorithm itself—so critical, in fact, that when these parameters are pushed to their limits, we are able to achieve state-of-theart performance on both CIFAR and NORB using only a single layer of features. More surprisingly, our best performance is based on K-means clustering, which is extremely fast, has no hyper-parameters to tune beyond the model structure itself, and is very easy implement. Despite the simplicity of our system, we achieve performance beyond all previously published results on the CIFAR-10 and NORB datasets (79.6 % and 97.0 % accuracy respectively). 1
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
"... We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be repurposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks an ..."
Abstract
-
Cited by 203 (22 self)
- Add to MetaCart
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be repurposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks and there may be insufficient labeled or unlabeled data to conventionally train or adapt a deep architecture to the new tasks. We investigate and visualize the semantic clustering of deep convolutional features with respect to a variety of such tasks, including scene recognition, domain adaptation, and fine-grained recognition challenges. We compare the efficacy of relying on various network levels to define a fixed feature, and report novel results that significantly outperform the state-of-the-art on several important vision challenges. We are releasing DeCAF, an open-source implementation of these deep convolutional activation features, along with all associated network parameters to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms. 1.
Building high-level features using large scale unsupervised learning
- In International Conference on Machine Learning, 2012. 103
"... We consider the problem of building highlevel, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder withpoolingandlocalcontrastnormalizati ..."
Abstract
-
Cited by 180 (9 self)
- Add to MetaCart
(Show Context)
We consider the problem of building highlevel, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder withpoolingandlocalcontrastnormalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel images downloaded from the Internet). We train this network using model parallelism and asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containingafaceornot. Controlexperiments show that this feature detector is robust not only to translation but also to scaling and out-of-plane rotation. We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained our network to obtain 15.8 % accuracy in recognizing 20,000 object categories from ImageNet, a leap of 70 % relative improvement over the previous state-of-the-art.
Representation learning: A review and new perspectives.
- of IEEE Conf. Comp. Vision Pattern Recog. (CVPR),
, 2005
"... Abstract-The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can b ..."
Abstract
-
Cited by 173 (4 self)
- Add to MetaCart
(Show Context)
Abstract-The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks. This motivates longer term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation, and manifold learning.
Overfeat: Integrated recognition, localization and detection using convolutional networks
- http://arxiv.org/abs/1312.6229
"... ar ..."
(Show Context)
Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair
"... Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these “Stepped Si ..."
Abstract
-
Cited by 154 (8 self)
- Add to MetaCart
(Show Context)
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these “Stepped Sigmoid Units ” are unchanged. They can be approximated efficiently by noisy, rectified linear units. Compared with binary units, these units learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset. Unlike binary units, rectified linear units preserve information about relative intensities as information travels through multiple layers of feature detectors. 1.
The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization
, 2011
"... While vector quantization (VQ) has been applied widely to generate features for visual recognition problems, much recent work has focused on more powerful methods. In particular, sparse coding has emerged as a strong alternative to traditional VQ approaches and has been shown to achieve consistently ..."
Abstract
-
Cited by 149 (7 self)
- Add to MetaCart
(Show Context)
While vector quantization (VQ) has been applied widely to generate features for visual recognition problems, much recent work has focused on more powerful methods. In particular, sparse coding has emerged as a strong alternative to traditional VQ approaches and has been shown to achieve consistently higher performance on benchmark datasets. Both approaches can be split into a training phase, where the system learns a dictionary of basis functions, and an encoding phase, where the dictionary is used to extract features from new inputs. In this work, we investigate the reasons for the success of sparse coding over VQ by decoupling these phases, allowing us to separate out the contributions of training and encoding in a controlled way. Through extensive experiments on CIFAR, NORB and Caltech 101 datasets, we compare several training and encoding schemes, including sparse coding and a form of VQ with a soft threshold activation function. Our results show not only that we can use fast VQ algorithms for training, but that we can just as well use randomly chosen exemplars from the training set. Rather than spend resources on training, we find it is more important to choose a good encoder—which can often be a simple feed forward non-linearity. Our results include state-of-the-art performance on both CIFAR and NORB.
