Context-conditional adaptation for recognizing unseen classes in unseen domains

Puneet Mangla, Indian Institute of Technology
Shivam Chandhok, Mohamed bin Zayed University of Artificial Intelligence
Vineeth N. Balasubramanian, Indian Institute of Technology
Fahad Shahbaz Khan, Mohamed bin Zayed University of Artificial Intelligence

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC by 4.0

Uploaded 24 March 2022


Recent progress towards designing models that can generalize to unseen domains (i.e domain generalization) or unseen classes (i.e zero-shot learning) has embarked interest towards building models that can tackle both domain-shift and semantic shift simultaneously (i.e zero-shot domain generalization). For models to generalize to unseen classes in unseen domains, it is crucial to learn feature representation that preserves class-level (domain-invariant) as well as domain-specific information. Motivated from the success of generative zero-shot approaches, we propose a feature generative framework integrated with a COntext COnditional Adaptive (COCOA) Batch-Normalization to seamlessly integrate class-level semantic and domain-specific information. The generated visual features better capture the underlying data distribution enabling us to generalize to unseen classes and domains at test-time. We thoroughly evaluate and analyse our approach on established large-scale benchmark - DomainNet and demonstrate promising performance over baselines and state-of-art methods. © 2021, CC BY.