Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks
Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough agreement on an augmentation scheme that optimises popular recognition benchmarks. However, there is strong reason to suspect that different tasks in computer vision require features to encode different (in)variances, and therefore likely require different augmentation strategies. In this paper, we measure the invariances learned by contrastive methods and confirm that they do learn invariance to the augmentations used and further show that this invariance largely transfers to related real-world changes in pose and lighting. We show that learned invariances strongly affect downstream task performance and confirm that different downstream tasks benefit from polar opposite (in)variances, leading to performance loss when the standard augmentation strategy is used. Finally, we demonstrate that a simple fusion of representations with complementary invariances ensures wide transferability to all the diverse downstream tasks considered.
Code (1)
Tasks
Data AugmentationRepresentation LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Self-Supervised Learning of Video-Induced Visual Invariances
We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI). We consider the implicit hierarchy present in the videos and make use o…
Image ClassificationSelf-Supervised LearningTransfer LearningUnderstanding Cross-Model Perceptual Invariances Through Ensemble Metamers
Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identica…
Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations
Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruction-based learning (e.g., BEiT, SimMIM, MAE) are the two leading paradigms for self-supervised learning of vision transformers, but they differ sub…
Self-Supervised LearningSpecificityMasked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. Thi…
Self-Supervised LearningArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and t…
Contrastive LearningData AugmentationSelf-Supervised Learning