Class Similarity Transition: Decoupling Class Similarities and Imbalance from Generalized Few-shot Segmentation

Shihong Wang, Ruixun Liu, Kaiyu Li, Jiawei Jiang, Xiangyong Cao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 2762-2770

In Generalized Few-shot Segmentation (GFSS) a model is trained with a large set of base class samples and then adapted on limited samples of novel classes. This paper focuses on the relevance between base and novel classes and improves GFSS in two aspects: 1) mining the similarity between base and novel classes to promote the learning of novel classes and 2) mitigating the class imbalance issue caused by the volume difference between the support set and the training set. Specifically we first propose a similarity transition matrix to guide the learning of novel classes with base class knowledge. Then we leverage the Label-Distribution-Aware Margin (LDAM) loss and Transductive Inference to the GFSS task to address the problem of class imbalance as well as overfitting the support set. In addition by extending the probability transition matrix the proposed method can mitigate the catastrophic forgetting of base classes when learning novel classes. With a simple training phase our proposed method can be applied to any segmentation network trained on base classes. We validated our methods on the adapted version of Ope- nEarthMap. Compared to existing GFSS baselines our method excels them all from 3% to 7% and ranks second in the OpenEarthMap Land Cover Mapping Few-Shot Challenge at the completion of this paper.