Generalized Few-Shot Semantic Segmentation

10/11/2020
by   Zhuotao Tian, et al.
5

Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS-Seg), to analyze the generalization ability of segmentation models to simultaneously recognize novel categories with very few examples as well as base categories with sufficient examples. Previous state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained training setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, as context is the key for boosting performance on semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by leveraging the contextual information to update class prototypes with aligned features. Extensive experiments on Pascal-VOC and COCO manifest the effectiveness of CAPL, and CAPL also generalizes well to FS-Seg.

READ FULL TEXT

page 3

page 5

page 6

research
03/24/2023

Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation

Current methods for few-shot segmentation (FSSeg) have mainly focused on...
research
08/09/2023

Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation

Generalized Few-shot Semantic Segmentation (GFSS) extends Few-shot Seman...
research
06/01/2021

Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Encouraging progress in few-shot semantic segmentation has been made by ...
research
11/16/2022

Interclass Prototype Relation for Few-Shot Segmentation

Traditional semantic segmentation requires a large labeled image dataset...
research
01/19/2023

FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

Few-shot semantic segmentation is the task of learning to locate each pi...
research
10/08/2022

Sequential Ensembling for Semantic Segmentation

Ensemble approaches for deep-learning-based semantic segmentation remain...
research
05/18/2023

Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation

Incremental few-shot semantic segmentation (IFSS) aims to incrementally ...

Please sign up or login with your details

Forgot password? Click here to reset