DeepAI AI Chat
Log In Sign Up

Towards Shape Biased Unsupervised Representation Learning for Domain Generalization

by   Nader Asadi, et al.
Shahid Bahonar University of Kerman
University of Manitoba

It is known that, without awareness of the process, our brain appears to focus on the general shape of objects rather than superficial statistics of context. On the other hand, learning autonomously allows discovering invariant regularities which help generalization. In this work, we propose a learning framework to improve the shape bias property of self-supervised methods. Our method learns semantic and shape biased representations by integrating domain diversification and jigsaw puzzles. The first module enables the model to create a dynamic environment across arbitrary domains and provides a domain exploration vs. exploitation trade-off, while the second module allows the model to explore this environment autonomously. This universal framework does not require prior knowledge of the domain of interest. Extensive experiments are conducted on several domain generalization datasets, namely, PACS, Office-Home, VLCS, and Digits. We show that our framework outperforms state-of-the-art domain generalization methods by a large margin.


page 1

page 3

page 8


Progressive Domain Expansion Network for Single Domain Generalization

Single domain generalization is a challenging case of model generalizati...

Robust Representation Learning with Self-Distillation for Domain Generalization

Domain generalization is a challenging problem in machine learning, wher...

Dual Reweighting Domain Generalization for Face Presentation Attack Detection

Face anti-spoofing approaches based on domain generalization (DG) have d...

MonoFormer: Towards Generalization of self-supervised monocular depth estimation with Transformers

Self-supervised monocular depth estimation has been widely studied recen...

Style Variable and Irrelevant Learning for Generalizable Person Re-identification

Recently, due to the poor performance of supervised person re-identifica...

Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

We introduce a novel unsupervised domain adaptation approach for object ...

Domain Generalization by Solving Jigsaw Puzzles

Human adaptability relies crucially on the ability to learn and merge kn...