Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation
This addresses the challenge of maintaining base class performance while improving novel class segmentation in few-shot learning, which is incremental as it builds on existing prototype-based methods.
The paper tackles the problem of generalized few-shot semantic segmentation, where current methods neglect base class performance, by proposing a class-contrastive approach that regulates prototype updates to distinguish classes. The approach achieves new state-of-the-art performance on PASCAL VOC and MS COCO datasets.
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.