Object-aware Contrastive Learning for Debiased Scene Representation

07/30/2021
by   Sangwoo Mo, et al.
3

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often contextually biased to the spurious scene correlations of different objects or object and background, which may harm their generalization on the downstream tasks. To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data augmentations considering the inferred object locations. For (a), we propose the contrastive class activation map (ContraCAM), which finds the most discriminative regions (e.g., objects) in the image compared to the other images using the contrastively trained models. We further improve the ContraCAM to detect multiple objects and entire shapes via an iterative refinement procedure. For (b), we introduce two data augmentations based on ContraCAM, object-aware random crop and background mixup, which reduce contextual and background biases during contrastive self-supervised learning, respectively. Our experiments demonstrate the effectiveness of our representation learning framework, particularly when trained under multi-object images or evaluated under the background (and distribution) shifted images.

READ FULL TEXT

page 4

page 6

page 15

page 16

page 17

page 18

page 19

page 20

research
06/22/2021

Unsupervised Object-Level Representation Learning from Scene Images

Contrastive self-supervised learning has largely narrowed the gap to sup...
research
06/10/2019

Online Object Representations with Contrastive Learning

We propose a self-supervised approach for learning representations of ob...
research
03/06/2023

Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

Self-supervised Learning (SSL) provides a strategy for constructing usef...
research
05/30/2023

A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play

Research in child development has shown that embodied experience handlin...
research
03/20/2022

SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization

Recently self-supervised representation learning has drawn considerable ...
research
11/16/2022

Boosting Object Representation Learning via Motion and Object Continuity

Recent unsupervised multi-object detection models have shown impressive ...
research
07/27/2022

Time to augment contrastive learning

Biological vision systems are unparalleled in their ability to learn vis...

Please sign up or login with your details

Forgot password? Click here to reset