Paper Image

Classic test-time adaptation methods fail for semantic segmentation

Published on:

9 October 2023

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Chang'an Yi,

Haotian Chen,

Yifan Zhang,

Yonghui Xu,

Lizhen Cui


Key Details

Batch norm updating is ineffective for segmentation TTA

Teacher-student stabilizes but does not improve segmentation TTA

Severe long-tail challenge in segmentation TTA

Test augmentation partially relieves long-tail issue

Classic TTA methods fail for segmentation tasks

AI generated summary

Classic test-time adaptation methods fail for semantic segmentation

This paper systematically investigates classic test-time adaptation (TTA) methods for semantic segmentation. Through extensive experiments, it finds that techniques effective for classification TTA, like batch norm updating and teacher-student schemes, do not work well for segmentation. Key challenges are inaccurate distribution estimation and long-tailed class imbalance. The paper provides insights to guide future segmentation TTA research.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up