Revisiting Self-Supervised Visual Representation Learning

Abstract

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging benchmarks. A large number of the pretext tasks for self-supervised learning have been studied, but other important aspects, such as the choice of convolutional neural networks (CNN), has not received equal attention. Therefore, we revisit numerous previously proposed self-supervised models, conduct a thorough large scale study and, as a result, uncover multiple crucial insights. We challenge a number of common practices in selfsupervised visual representation learning and observe that standard recipes for CNN design do not always translate to self-supervised representation learning. As part of our study, we drastically boost the performance of previously proposed techniques and outperform previously published state-of-the-art results by a large margin.

All three authors contributed equally. Code is available at https://github.com/google/revisiting-self-supervised

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (8)

• Learning Representations by Maximizing Mutual Information Across Views
• Self-labelling via simultaneous clustering and representation learning
• Two Stream Networks for Self-Supervised Ego-Motion Estimation
• CSNNs: Unsupervised, Backpropagation-free Convolutional Neural Networks for Representation Learning
• ClusterFit: Improving Generalization of Visual Representations
• Boosting Supervision with Self-Supervision for Few-shot Learning
• Towards a Hypothesis on Visual Transformation based Self-Supervision
• AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups