A Strong Baseline for Generalized Few-Shot Semantic Segmentation
This work addresses the problem of segmenting novel objects with limited examples for computer vision researchers, but it is incremental as it builds on existing few-shot segmentation methods.
The paper tackles generalized few-shot semantic segmentation by proposing a simple framework based on the InfoMax principle and knowledge distillation, achieving improvements of 7% to 26% on PASCAL-5^i and 3% to 12% on COCO-20^i for novel classes in 1-shot and 5-shot scenarios.
This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-$5^i$ and COCO-$20^i$. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-$5^i$) and from 3% to 12% (COCO-$20^i$) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.