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.
© 1979-2012 IEEE.Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of seen primitives. Prior studies have attempted to either learn primitives individually (non-connected) or establish dependencies among them in the composition (fully-connected). In contrast, human comprehension of composition diverges from the aforementioned methods as humans possess the ability to make composition-aware adaptation for these primitives, instead of inferring them rigidly through the aforementioned methods. However, developing a comprehension of compositions akin to human cognition proves challenging within the confines of real space. This arises from the limitation of real-space-based methods, which often categorize attributes, objects, and compositions using three independent measures, without establishing a direct dynamic connection. To tackle this challenge, we expand the CZSL distance metric scheme to encompass complex spaces to unify the independent measures, and we establish an imaginary-connected embedding in complex space to model human understanding of attributes. To achieve this representation, we introduce an innovative visual bias-based attribute extraction module that selectively extracts attributes based on object prototypes. As a result, we are able to incorporate phase information in training and inference, serving as a metric for attribute-object dependencies while preserving the independent acquisition of primitives. We evaluate the effectiveness of our proposed approach on three benchmark datasets, illustrating its superiority compared to baseline methods. Our code is available at https://github.com/LanchJL/IMAX.
Author(s): Jiang C, Wang S, Long Y, Li Z, Zhang H, Shao L
Publication type: Article
Publication status: Published
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2024
Pages: epub ahead of print
Online publication date: 29/10/2024
Acceptance date: 02/04/2018
ISSN (print): 0162-8828
ISSN (electronic): 1939-3539
Publisher: IEEE Computer Society
URL: https://doi.org/10.1109/TPAMI.2024.3487631
DOI: 10.1109/TPAMI.2024.3487631
Altmetrics provided by Altmetric
