Posted Content•
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
TL;DR: This work introduces Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning that performs on par or better than the current state of the art on both transfer and semi- supervised benchmarks.
Abstract: We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches $74.3\%$ top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and $79.6\%$ with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks. Our implementation and pretrained models are given on GitHub.
Citations
More filters
Posted Content•
TL;DR: Surprising empirical results are reported that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders.
Abstract: Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code will be made available.
1,733 citations
Cites background or methods from "Bootstrap Your Own Latent: A New Ap..."
...1MoCo [17] and BYOL [15] do not directly share the weights between the two branches, though in theory the momentum encoder should converge to the same status as the trainable encoder....
[...]
...clustering, BYOL [15] relies only on positive pairs but it does not collapse in case a momentum encoder is used....
[...]
...We use batch normalization (BN) [22] synchronized across devices, following [8, 15, 7]....
[...]
...A prediction MLP head [15], denoted as h, transforms the output of one view and matches it to the other view....
[...]
...Our method does not require a large-batch optimizer such as LARS [38] (unlike [8, 15, 7])....
[...]
Posted Content•
TL;DR: This work investigates the effects of several fundamental components for training self-supervised ViT, and reveals that these results are indeed partial failure, and they can be improved when training is made more stable.
Abstract: This paper does not describe a novel method Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT) While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT We observe that instability is a major issue that degrades accuracy, and it can be hidden by apparently good results We reveal that these results are indeed partial failure, and they can be improved when training is made more stable We benchmark ViT results in MoCo v3 and several other self-supervised frameworks, with ablations in various aspects We discuss the currently positive evidence as well as challenges and open questions We hope that this work will provide useful data points and experience for future research
949 citations
Cites background or methods from "Bootstrap Your Own Latent: A New Ap..."
...the big convolutional ResNets in prior art [10, 17]....
[...]
...We adopt a symmetrized loss [17, 7, 12]: ctr(q1, k2)+ctr(q2, k1)....
[...]
...A large batch is also beneficial for accuracy in recent selfsupervised learning methods [9, 17, 7]....
[...]
...prior works [8, 15] that train self-supervised Transformers with masked auto-encoding, we study the frameworks that are based on Siamese networks, including MoCo [19] and others [9, 17, 7]....
[...]
...lr is the hyper-parameter being set [19, 9, 17]....
[...]
01 Jun 2021
TL;DR: SimSiam as discussed by the authors proposes to use a stop-gradient operation to prevent collapsing solutions in Siamese networks, which achieves competitive results on ImageNet and downstream tasks, and further shows proof-of-concept experiments verifying it.
Abstract: Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code is made available.1
754 citations
20 Jun 2021
TL;DR: BoTNet as mentioned in this paper incorporates self-attention for image classification, object detection, and instance segmentation, and achieves state-of-the-art performance on the ImageNet benchmark.
Abstract: We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet and no other changes, our approach improves upon the baselines significantly on instance segmentation and object detection while also reducing the parameters, with minimal overhead in latency. Through the design of BoTNet, we also point out how ResNet bottleneck blocks with self-attention can be viewed as Transformer blocks. Without any bells and whistles, BoTNet achieves 44.4% Mask AP and 49.7% Box AP on the COCO Instance Segmentation benchmark using the Mask R-CNN framework; surpassing the previous best published single model and single scale results of ResNeSt [67] evaluated on the COCO validation set. Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84.7% top-1 accuracy on the ImageNet benchmark while being up to 1.64x faster in "compute"1 time than the popular EfficientNet models on TPU-v3 hardware. We hope our simple and effective approach will serve as a strong baseline for future research in self-attention models for vision.2
675 citations
26 Feb 2021
TL;DR: The authors reviewed fundamental concepts of causal inference and related them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research.
Abstract: The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and increasing interest in both fields to benefit from the advances of the other. In this article, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, that is, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.
601 citations
References
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•
04 Sep 2014TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small 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.
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.
55,235 citations
"Bootstrap Your Own Latent: A New Ap..." refers background in this paper
...Learning good image representations is a key challenge in computer vision [1, 2, 3] as it allows for efficient training on downstream tasks [4, 5, 6, 7]....
[...]
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
08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Abstract: We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to ½ everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
38,211 citations
"Bootstrap Your Own Latent: A New Ap..." refers background in this paper
...This is similar to GANs [66], where there is no loss that is jointly minimized w....
[...]
...This is similar to GANs [66], where there is no loss that is jointly minimized w.r.t. both the discriminator and generator parameters....
[...]
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
"Bootstrap Your Own Latent: A New Ap..." refers methods in this paper
...This MLP consists in a linear layer with output size 4096 followed by batch normalization [55], rectified linear units (ReLU) [56], and a final linear layer with output dimension 256....
[...]