.png){kind=icon}
Return
Dual-Stream Contrastive Learning for Compositional Zero-Shot Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2023.3243674.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Compositional Zero-Shot learning (CZSL) requires recognizing unseen attribute-object compositions using observed visual primitives attributes and objects in a training set, which is a critical capacity for learning systems because the long tail of new combinations dominates the distribution in the real world. However, CZSL is a challenging problem because learning systems tend to learn the dependencies between objects and attributes, which is not conducive to composition classification, and incorrect dependencies will mislead the classification of new combinations of known attributes and objects. This paper primarily introduces a novel yet effective dual-stream contrastive learning method with two main objectives: making the learned representations discriminative and transferring knowledge more efficiently from seen to unseen compositions. Specifically, we generate positive and negative pairs based on the similarity of different concepts (attributes and objects), independently capturing the discriminative representations of concepts. Meanwhile, unlike existing contrastive methods that select negative samples randomly, we construct confusable compositional representations as the negatives to explore the intrinsic relevance between attributes and objects, which can improve the generalization from seen to unseen compositions. Experimental results on two benchmarks show that the proposed method outperforms the state-of-the-arts.
Keywords:
Compositional Zero-Shot learning
contrastive learning
transfer learning
Journal
IF:
9.7
Papers:
4.7K
Citations:
2.4W
Organization
Cited Papers
.png){kind=icon}
Removal of methylene blue from colored effluents by adsorption onto ZnAPSO-34 nanoporous material
OAAI
OAAIShareSaveShareSave
View more