Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation

TL;DR

This paper introduces Uncertainty-aware Contrastive Distillation, a novel method for incremental semantic segmentation that leverages contrastive learning and uncertainty to reduce catastrophic forgetting and improve performance.

Contribution

It proposes a new contrastive distillation framework that considers all pixel features in a mini-batch and uses a frozen model for feature comparison, advancing incremental segmentation methods.

Findings

Achieves state-of-the-art results on three benchmarks.

Effectively mitigates catastrophic forgetting in incremental segmentation.

Can be combined with existing IL approaches for improved performance.

Abstract

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years. While earlier works in computer vision have mostly focused on image classification and object detection, more recently some IL approaches for semantic segmentation have been introduced. These previous works showed that, despite its simplicity, knowledge distillation can be effectively employed to alleviate catastrophic forgetting. In this paper, we follow this research direction and, inspired by recent literature on contrastive learning, we propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (\method). In a nutshell, \method~is operated by introducing a novel distillation loss that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes. In order to mitigate catastrophic forgetting, we contrast features of the new model with features extracted by a frozen model learned at the previous incremental step. Our experimental results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches, and leads to state-of-art performance on three commonly adopted benchmarks for incremental semantic segmentation. The code is available at \url{https://github.com/ygjwd12345/UCD}.