A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
Keywords: few-shot learning, semantic segmentation, catastrophic forgetting
TL;DR: A simple approach without resorting to, e.g., complicated modules and meta-learning improved GFSS performance.
Abstract: The goal of *generalized* few-shot semantic segmentation (GFSS) is to recognize *novel-class* objects through training with a few annotated examples and the *base-class* model that learned the knowledge about the base classes.
Unlike the classic few-shot semantic segmentation, GFSS aims to classify pixels into both base and novel classes, meaning it is a more practical setting.
Current GFSS methods rely on several techniques such as using combinations of customized modules, carefully designed loss functions, meta-learning, and transductive learning.
However, we found that a simple rule and standard supervised learning substantially improve the GFSS performance.
In this paper, we propose a simple yet effective method for GFSS that does not use the techniques mentioned above.
Also, we theoretically show that our method perfectly maintains the segmentation performance of the base-class model over most of the base classes.
Through numerical experiments, we demonstrated the effectiveness of our method.
It improved in novel-class segmentation performance in the $1$-shot scenario by $6.1$% on the PASCAL-$5^i$ dataset, $4.7$% on the PASCAL-$10^i$ dataset, and $1.0$% on the COCO-$20^i$ dataset.
Our code is publicly available at https://github.com/IBM/BCM.
Primary Area: Machine vision
Submission Number: 5788
Loading