Towards Recognizing Unseen Categories in Unseen Domains
Current deep visual recognition systems suffer from severe performance degradation when they encounter new images from classes and scenarios unseen during training. Hence, the core challenge of Zero-Shot Learning (ZSL) is to cope with the semantic-shift whereas the main challenge of Domain Adaptation and Domain Generalization (DG) is the domain-shift. While historically ZSL and DG tasks are tackled in isolation, this work develops with the ambitious goal of solving them jointly,i.e. by recognizing unseen visual concepts in unseen domains. We presentCuMix (CurriculumMixup for recognizing unseen categories in unseen domains), a holistic algorithm to tackle ZSL, DG and ZSL+DG. The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories generated by mixing up the multiple source domains and categories available during training. Moreover, a curriculum-based mixing policy is devised to generate increasingly complex training samples. Results on standard SL and DG datasets and on ZSL+DG using the DomainNet benchmark demonstrate the effectiveness of our approach.
Code (1)
Tasks
Domain GeneralizationZero-Shot LearningZero-Shot Learning + Domain GeneralizationSimilar Papers 제목 키워드 기반
Distinguishing Unseen From Seen for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to recognize samples whose categories may not have been seen at training. Recognizing unseen classes as seen ones or vice versa often leads to poor performance in GZSL. Ther…
Generalized Zero-Shot LearningZero-Shot LearningCreativity Inspired Zero-Shot Learning
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of…
AttributeTransfer LearningZero-Shot LearningContext-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains
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 dom…
Domain GeneralizationZero-Shot LearningZero-Shot Learning + Domain GeneralizationFew-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains
Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest. Though several approaches have been proposed, most existing few-shot learning (FSL) models assume t…
ClassificationFew-Shot LearningGeneralized Few-Shot ClassificationMeta-Learning+1Transductive Universal Transport for Zero-Shot Action Recognition
This work addresses the problem of recognizing action categories in videos for which no training examples are available. The current state-of-the-art enables such a zero-shot recognition by learning universal mappings fr…
Action RecognitionObjectPositionTemporal Localization+3