Zero-Forgetting CISS via Dual-Phase Cognitive Cascades

TL;DR

This paper introduces CogCaS, a dual-phase cascade approach inspired by human cognition, to improve continual semantic segmentation by reducing catastrophic forgetting and effectively learning new classes.

Contribution

The paper proposes a novel dual-phase cascade framework, CogCaS, that decouples class detection and segmentation to enhance continual learning in semantic segmentation.

Findings

Significant performance improvements on PASCAL VOC 2012 and ADE20K datasets.

Better handling of long sequences of incremental tasks.

Outperforms existing state-of-the-art methods in CISS.

Abstract

Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge. In conventional class-incremental semantic segmentation (CISS) frameworks using Softmax-based classification heads, catastrophic forgetting originates from Catastrophic forgetting and task affiliation probability. We formulate these problems and provide a theoretical analysis to more deeply understand the limitations in existing CISS methods, particularly Strict Parameter Isolation (SPI). To address these challenges, we follow a dual-phase intuition from human annotators, and introduce Cognitive Cascade Segmentation (CogCaS), a novel dual-phase cascade formulation for CSS tasks in the CISS setting. By decoupling the task into class-existence detection and class-specific segmentation, CogCaS enables more effective continual learning, preserving previously learned knowledge while incorporating new classes. Using two benchmark datasets PASCAL VOC 2012 and ADE20K, we have shown significant improvements in a variety of challenging scenarios, particularly those with long sequence of incremental tasks, when compared to exsiting state-of-the-art methods. Our code will be made publicly available upon paper acceptance.