.png){kind=icon}
.png){kind=icon}
Return
Frequency-Based Matcher for Long-Tailed Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2024.3407679.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The successful application of semantic segmentation technology in the real world has been among the most exciting achievements in the computer vision community over the past decade. Although the long-tailed phenomenon has been investigated in many fields, e.g., classification and object detection, it has not received enough attention in semantic segmentation and has become a nonnegligible obstacle to applying semantic segmentation technology in autonomous driving and virtual reality. Therefore, in this work, we focus on a relatively underexplored task setting, long-tailed semantic segmentation (LTSS). We first establish three representative datasets from different aspects, i.e., scene, object, and human. We further propose a dual-metric evaluation system and construct the LTSS benchmark to demonstrate the performance of semantic segmentation methods and long-tailed solutions. We also propose a transformer-based algorithm to improve LTSS, frequency-based matcher, which solves the oversuppression problem by one-to-many matching and automatically determines the number of matching queries for each class. Given the comprehensiveness of this work and the importance of the issues revealed, this work aims to promote the empirical study of semantic segmentation tasks.
Keywords:
Semantic segmentation
Task analysis
Transformers
Image segmentation
Semantics
Tail
Decoding
long-tailed learning
frequency-based matcher
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W