4 papers
Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning
Yang Liu, Wentao Feng, Shu-Dong Huang +2
Large-scale web-harvested datasets have fueled the progress of cross-modal retrieval but inevitably suffer from noisy correspondence, which severely degrades model generalization.…
PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
Zhuoyao Liu, Yang Liu, Wentao Feng +1
Cross-modal retrieval aims to align different modalities via semantic similarity. However, existing methods often assume that image-text pairs are perfectly aligned, overlooking No…
Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching
Yang Liu, Wentao Feng, Zhuoyao Liu +2
Enabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge. Existing methods typically learn a set of embeddings to fin…
Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
Yang Liu, Mengyuan Liu, Shudong Huang +1
Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data,…