Papers
arxiv:2203.05402

Representation Compensation Networks for Continual Semantic Segmentation

Published on Mar 10, 2022
Authors:
,
,
,

Abstract

A structural re-parameterization representation compensation module and pooled cube knowledge distillation enable continual semantic segmentation to learn new classes without catastrophic forgetting and without extra inference cost.

In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at https://github.com/zhangchbin/RCIL.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2203.05402
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2203.05402 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2203.05402 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2203.05402 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.