Directional Self-supervised Learning for Risky Image Augmentations

by   Yalong Bai, et al.
Peking University

Only a few cherry-picked robust augmentation policies are beneficial to standard self-supervised image representation learning, despite the large augmentation family. In this paper, we propose a directional self-supervised learning paradigm (DSSL), which is compatible with significantly more augmentations. Specifically, we adapt risky augmentation policies after standard views augmented by robust augmentations, to generate harder risky view (RV). The risky view usually has a higher deviation from the original image than the standard robust view (SV). Unlike previous methods equally pairing all augmented views for symmetrical self-supervised training to maximize their similarities, DSSL treats augmented views of the same instance as a partially ordered set (SV↔SV, SV←RV), and then equips directional objective functions respecting to the derived relationships among views. DSSL can be easily implemented with a few lines of Pseudocode and is highly flexible to popular self-supervised learning frameworks, including SimCLR, SimSiam, BYOL. The extensive experimental results on CIFAR and ImageNet demonstrated that DSSL can stably improve these frameworks with compatibility to a wider range of augmentations.


Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation

Sequential Recommendation aims to predict the next item based on user be...

ViewMix: Augmentation for Robust Representation in Self-Supervised Learning

Joint Embedding Architecture-based self-supervised learning methods have...

Broaden Your Views for Self-Supervised Video Learning

Most successful self-supervised learning methods are trained to align th...

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Self-supervised learning (SSL) has delivered superior performance on a v...

MSR: Making Self-supervised learning Robust to Aggressive Augmentations

Most recent self-supervised learning methods learn visual representation...

Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction

State-of-the-art methods for self-supervised learning (SSL) build repres...

AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image

Multiple Instance Learning (MIL), a powerful strategy for weakly supervi...

Please sign up or login with your details

Forgot password? Click here to reset