HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
By: Vaibhav Rathore, Divyam Gupta, Biplab Banerjee
Potential Business Impact:
Helps computers learn new things without seeing examples.
Generalized Category Discovery (GCD) aims to classify test-time samples into either seen categories** -- available during training -- or novel ones, without relying on label supervision. Most existing GCD methods assume simultaneous access to labeled and unlabeled data during training and arising from the same domain, limiting applicability in open-world scenarios involving distribution shifts. Domain Generalization with GCD (DG-GCD) lifts this constraint by requiring models to generalize to unseen domains containing novel categories, without accessing targetdomain data during training. The only prior DG-GCD method, DG2CD-Net, relies on episodic training with multiple synthetic domains and task vector aggregation, incurring high computational cost and error accumulation. We propose HIDISC, a hyperbolic representation learning framework that achieves domain and category-level generalization without episodic simulation. To expose the model to minimal but diverse domain variations, we augment the source domain using GPT-guided diffusion, avoiding overfitting while maintaining efficiency. To structure the representation space, we introduce Tangent CutMix, a curvature-aware interpolation that synthesizes pseudo-novel samples in tangent space, preserving manifold consistency. A unified loss -- combining penalized Busemann alignment, hybrid hyperbolic contrastive regularization, and adaptive outlier repulsion -- **facilitates compact, semantically structured embeddings. A learnable curvature parameter further adapts the geometry to dataset complexity. HIDISC achieves state-of-the-art results on PACS , Office-Home , and DomainNet, consistently outperforming the existing Euclidean and hyperbolic (DG)-GCD baselines.
Similar Papers
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach
CV and Pattern Recognition
Teaches computers to find new things without seeing them.
Hyperbolic Category Discovery
CV and Pattern Recognition
Helps computers understand new things they haven't seen.
Generative Classifier for Domain Generalization
CV and Pattern Recognition
Teaches computers to see better in new places.