Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains

TL;DR

This paper introduces a feature generative framework with context-conditional adaptive batch normalization to improve recognition of unseen classes across unseen domains, addressing both domain and semantic shifts.

Contribution

It proposes a novel feature generation method combined with context-conditional adaptive batch normalization for zero-shot domain generalization.

Findings

Achieves superior performance on DomainNet benchmark.

Effectively captures class-level and domain-specific features.

Outperforms existing state-of-the-art methods.

Abstract

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.