ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
By: Kailin Lyu , Jianwei He , Long Xiao and more
Potential Business Impact:
Helps computers learn new things without forgetting old ones.
In open-world scenarios, Generalized Category Discovery (GCD) requires identifying both known and novel categories within unlabeled data. However, existing methods often suffer from prototype confusion caused by shortcut learning, which undermines generalization and leads to forgetting of known classes. We propose ClearGCD, a framework designed to mitigate reliance on non-semantic cues through two complementary mechanisms. First, Semantic View Alignment (SVA) generates strong augmentations via cross-class patch replacement and enforces semantic consistency using weak augmentations. Second, Shortcut Suppression Regularization (SSR) maintains an adaptive prototype bank that aligns known classes while encouraging separation of potential novel ones. ClearGCD can be seamlessly integrated into parametric GCD approaches and consistently outperforms state-of-the-art methods across multiple benchmarks.
Similar Papers
Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
CV and Pattern Recognition
Helps computers find new things in videos.
Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
CV and Pattern Recognition
Helps computers learn new things like humans do.
ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery
Machine Learning (CS)
Helps computers learn new things from old examples.