This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.

A Simple Framework for Contrastive Learning of Visual Representations

While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations from high-dimensional data, which we call Contrastive Predictive Coding. The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models. We use a probabilistic contrastive loss which induces the latent space to capture information that is maximally useful to predict future samples. It also makes the model tractable by using negative sampling. While most prior work has focused on evaluating representations for a particular modality, we demonstrate that our approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.

Representation Learning with Contrastive Predictive Coding

This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

/pdf/orb-slam-a-versatile-and-accurate-monocular-slam-system-t5f1c0a74e.pdf

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

Momentum Contrast for Unsupervised Visual Representation Learning

/pdf/momentum-contrast-for-unsupervised-visual-representation-2eazkncurm.pdf

We propose a novel unsupervised learning approach to build features suitable for object detection and classification. The features are pre-trained on a large dataset without human annotation and later transferred via fine-tuning on a different, smaller and labeled dataset. The pre-training consists of solving jigsaw puzzles of natural images. To facilitate the transfer of features to other tasks, we introduce the context-free network (CFN), a siamese-ennead convolutional neural network. The features correspond to the columns of the CFN and they process image tiles independently (i.e., free of context). The later layers of the CFN then use the features to identify their geometric arrangement. Our experimental evaluations show that the learned features capture semantically relevant content. We pre-train the CFN on the training set of the ILSVRC2012 dataset and transfer the features on the combined training and validation set of Pascal VOC 2007 for object detection (via fast RCNN) and classification. These features outperform all current unsupervised features with \(51.8\,\%\) for detection and \(68.6\,\%\) for classification, and reduce the gap with supervised learning (\(56.5\,\%\) and \(78.2\,\%\) respectively).

/pdf/unsupervised-learning-of-visual-representations-by-solving-2mcv7t45u3.pdf

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

In this paper we study the problem of image representation learning without human annotation. By following the principles of self-supervision, we build a convolutional neural network (CNN) that can be trained to solve Jigsaw puzzles as a pretext task, which requires no manual labeling, and then later repurposed to solve object classification and detection. To maintain the compatibility across tasks we introduce the context-free network (CFN), a siamese-ennead CNN. The CFN takes image tiles as input and explicitly limits the receptive field (or context) of its early processing units to one tile at a time. We show that the CFN includes fewer parameters than AlexNet while preserving the same semantic learning capabilities. By training the CFN to solve Jigsaw puzzles, we learn both a feature mapping of object parts as well as their correct spatial arrangement. Our experimental evaluations show that the learned features capture semantically relevant content. Our proposed method for learning visual representations outperforms state of the art methods in several transfer learning benchmarks.

Portable light field (LF) cameras have demonstrated capabilities beyond conventional cameras. In a single snapshot, they enable digital image refocusing and 3D reconstruction. We show that they obtain a larger depth of field but maintain the ability to reconstruct detail at high resolution. In fact, all depths are approximately focused, except for a thin slab where blur size is bounded, i.e., their depth of field is essentially inverted compared to regular cameras. Crucial to their success is the way they sample the LF, trading off spatial versus angular resolution, and how aliasing affects the LF. We show that applying traditional multiview stereo methods to the extracted low-resolution views can result in reconstruction errors due to aliasing. We address these challenges using an explicit image formation model, and incorporate Lambertian and texture preserving priors to reconstruct both scene depth and its superresolved texture in a variational Bayesian framework, eliminating aliasing by fusing multiview information. We demonstrate the method on synthetic and real images captured with our LF camera, and show that it can outperform other computational camera systems.

The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution

http://www.vision.jhu.edu/assets/VidalPRL13.pdf

Low rank subspace clustering (LRSC)

We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.

Paolo Favaro

Papers

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution

Low rank subspace clustering (LRSC)

Representation Learning by Learning to Count