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 5% to 20% (PASCAL-$5^i$) and from 2.5% to 10.5% (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.

本文提出了一种基于InfoMax原理和互信息的模型，通过简单的训练过程和知识蒸馏项来改善少样本分割，在PASCAL-$5^i$和COCO-$20^i$这两个流行的分割基准上，针对新类别，1-shot和5-shot的情况下，性能提升范围从7％到26％（PASCAL-$5^i$）和从3％到12％（COCO-$20^i$），此外，文中还给出了一个更具挑战性的设置。

广义Few-Shot语义分割的强基准