Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
By: Ruitao Wu, Yifan Zhao, Jia Li
Potential Business Impact:
Teaches computers to learn new things without forgetting old ones.
Class-Incremental Semantic Segmentation (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes. By abstracting mainstream methods into two stages (visual feature extraction and prototype-feature matching), we identify a more fundamental challenge termed catastrophic semantic entanglement. This phenomenon involves Prototype-Feature Entanglement caused by semantic misalignment during the incremental process, and Background-Increment Entanglement due to dynamic data evolution. Existing techniques, which rely on visual feature learning without sufficient cues to distinguish targets, introduce significant noise and errors. To address these issues, we introduce a Language-inspired Bootstrapped Disentanglement framework (LBD). We leverage the prior class semantics of pre-trained visual-language models (e.g., CLIP) to guide the model in autonomously disentangling features through Language-guided Prototypical Disentanglement and Manifold Mutual Background Disentanglement. The former guides the disentangling of new prototypes by treating hand-crafted text features as topological templates, while the latter employs multiple learnable prototypes and mask-pooling-based supervision for background-incremental class disentanglement. By incorporating soft prompt tuning and encoder adaptation modifications, we further bridge the capability gap of CLIP between dense and sparse tasks, achieving state-of-the-art performance on both Pascal VOC and ADE20k, particularly in multi-step scenarios.
Similar Papers
Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation
CV and Pattern Recognition
Teaches computers to label images without pixel details.
Language-Guided Visual Perception Disentanglement for Image Quality Assessment and Conditional Image Generation
CV and Pattern Recognition
Helps computers see images better, not just understand them.
Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentation
CV and Pattern Recognition
Helps surgical robots learn new things without forgetting old ones.