FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

TL;DR

This paper introduces a novel fairness-aware continual learning method for semantic scene segmentation, addressing catastrophic forgetting, background shift, and fairness among classes, achieving state-of-the-art results on multiple benchmarks.

Contribution

It proposes a Fairness Contrastive Clustering loss and an attention-based visual grammar approach to improve fairness and unknown class modeling in continual semantic segmentation.

Findings

Achieves state-of-the-art performance on ADE20K, Cityscapes, and Pascal VOC.

Promotes fairness among major and minor classes in continual learning.

Effectively models background shift and unknown classes.

Abstract

Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and background shift challenges in continual learning. However, fairness, another major challenge that causes unfair predictions leading to low performance among major and minor classes, still needs to be well addressed. In addition, prior methods have yet to model the unknown classes well, thus resulting in producing non-discriminative features among unknown classes. This work presents a novel Fairness Learning via Contrastive Attention Approach to continual learning in semantic scene understanding. In particular, we first introduce a new Fairness Contrastive Clustering loss to address the problems of catastrophic forgetting and fairness. Then, we propose an attention-based visual grammar approach to effectively model the background shift problem and unknown classes, producing better feature representations for different unknown classes. Through our experiments, our proposed approach achieves State-of-the-Art (SoTA) performance on different continual learning benchmarks, i.e., ADE20K, Cityscapes, and Pascal VOC. It promotes the fairness of the continual semantic segmentation model.