![](https://d3ilqtpdwi981i.cloudfront.net/A0GJHVU7KDRBzVXTo4KilXmuQhQ=/425x550/smart/https://bepress-attached-resources.s3.amazonaws.com/uploads/dc/f5/22/dcf52286-4710-4d21-afd8-8cb5f3325909/thumbnail_e84b77bb-caee-46eb-bbbe-ba7e6f028879.jpg)
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
IR Deposit conditions: non-described
Open Access version available on CVF: