Browse by author
Lookup NU author(s): Dr Shidong WangORCiD
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known attribute-object pairs. The primary challenge in CZSL tasks lies in the significant discrepancies introduced by the complex interaction between the visual primitives of attribute and object, consequently decreasing the classification performance toward novel compositions. Previous remarkable works primarily addressed this issue by focusing on disentangling strategy or utilizing object-based conditional probabilities to constrain the selection space of attributes. Unfortunately, few studies have explored the problem from the perspective of modeling the mechanism of visual primitive interactions. Inspired by the success of vanilla adversarial learning in Cross-Domain Few-shot Learning, we take a step further and devise a model-agnostic and Primitive-based Adversarial Training (PBadv) method to deal with this problem. Besides, the latest studies highlight the weakness of the perception of hard compositions even under data-balanced conditions. To this end, we propose a novel over-sampling strategy with object-similarity guidance to augment target compositional training data. We performed detailed quantitative analysis and retrieval experiments on well-established datasets, such as UT-Zappos50K, MIT-States, and C-GQA, to validate the effectiveness of our proposed method, and the State-of-the-Art (SOTA) performance demonstrates the superiority of our approach. The code is available at https://github.com/lisuyi/PBadv_czsl.
Author(s): Li S, Jiang C, Wang S, Long Y, Zhang Z, Zhang H
Publication type: Article
Publication status: Published
Journal: ACM Transactions on Multimedia Computing, Communications and Applications
Year: 2025
Volume: 21
Issue: 10
Print publication date: 15/10/2025
Online publication date: 17/01/2025
Acceptance date: 11/01/2025
ISSN (print): 1551-6857
ISSN (electronic): 1551-6865
Publisher: Association for Computing Machinery
URL: https://doi.org/10.1145/3712596
DOI: 10.1145/3712596
Altmetrics provided by Altmetric
