Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels
Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we propose the Dynamic Visual-semantic Alignment (DVSA), a robust ZSL framework for learning from ambiguous labels. DVSA uses a bidirectional visual-semantic alignment module with attention to mutually calibrate visual features and attribute prototypes, and a contrastive optimization grounded in Mutual Information (MI) at the attribute level to strengthen discriminative, semantically consistent attributes. In addition, a dynamic label disambiguation mechanism iteratively corrects noisy supervision while preserving semantic consistency, narrowing the instance-label gap, and improving generalization. Extensive experiments on standard benchmarks verify that DVSA achieves stronger performance under ambiguous supervision.
Code (0)
등록된 구현이 없습니다.
Tasks
Zero-Shot LearningSimilar Papers 제목 키워드 기반
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Zero-shot action recognition, which addresses the issue of scalability and generalization in action recognition and allows the models to adapt to new and unseen actions dynamically, is an important research topic in comp…
Action RecognitionMetric LearningSkeleton Based Action RecognitionZero-Shot Action Recognition+1Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning
Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Exi…
Generalized Zero-Shot LearningZero-Shot LearningTokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection
Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse obj…
Semantic SimilarityAnomaly DetectionSemantically Grounded Visual Embeddings for Zero-Shot Learning
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learni…
Zero-Shot LearningDynamic Context-Aware Scene Reasoning Using Vision-Language Alignment in Zero-Shot Real-World Scenarios
In real-world environments, AI systems often face unfamiliar scenarios without labeled data, creating a major challenge for conventional scene understanding models. The inability to generalize across unseen contexts limi…
Zero-shot GeneralizationScene Understanding