2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
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 layer 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 our approach on established large-scale benchmarks - DomainNet, DomainNet-LS (Limited Sources) - as well as a new CUB-Corruptions benchmark, and demonstrate promising performance over baselines and state-of-the-art methods. We show detailed ablations and analysis to verify that our proposed approach indeed allows us to generate better quality visual features relevant for zero-shot domain generalization. © 2022 IEEE.
Benchmarking, Computer vision, Deep learning, Quality control, Class level, Domain-specific information, Few-shot, Generalisation, Recent progress, Semi- and un- supervised learning deep learning, Semi-supervised learning, Transfer, Un-supervised learning, Visual feature, Semantics
P. Mangla, S. Chandhok, V. N. Balasubramanian and F. Shahbaz Khan, "COCOA: Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains," in 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 3-8, 2022, WACV 2022, pp. 1618-1627, doi: 10.1109/WACV51458.2022.00168.