Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning

About

Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information. Prior works mainly localize regions corresponding to the sharing attributes. When various visual appearances correspond to the same attribute, the sharing attributes inevitably introduce semantic ambiguity, hampering the exploration of accurate semantic-visual interactions. In this paper, we deploy the dual semantic-visual transformer module (DSVTM) to progressively model the correspondences between attribute prototypes and visual features, constituting a progressive semantic-visual mutual adaption (PSVMA) network for semantic disambiguation and knowledge transferability improvement. Specifically, DSVTM devises an instance-motivated semantic encoder that learns instance-centric prototypes to adapt to different images, enabling the recast of the unmatched semantic-visual pair into the matched one. Then, a semantic-motivated instance decoder strengthens accurate cross-domain interactions between the matched pair for semantic-related instance adaption, encouraging the generation of unambiguous visual representations. Moreover, to mitigate the bias towards seen classes in GZSL, a debiasing loss is proposed to pursue response consistency between seen and unseen predictions. The PSVMA consistently yields superior performances against other state-of-the-art methods. Code will be available at: https://github.com/ManLiuCoder/PSVMA.

Man Liu, Feng Li, Chunjie Zhang, Yunchao Wei, Huihui Bai, Yao Zhao• 2023

Related benchmarks

TaskDatasetResultRank
Generalized Zero-Shot LearningCUB
H Score73.8
250
Generalized Zero-Shot LearningSUN
H52.3
184
Generalized Zero-Shot LearningAWA2
S Score77.3
165
Image ClassificationCUB
Unseen Top-1 Acc70.1
89
Image ClassificationAWA2 GZSL
Acc (Unseen)73.6
32
Image ClassificationSUN Attribute (test)
U Score61.7
19
Image ClassificationAWA2 v1 (test)
Score U73.6
19
Image ClassificationSUN GZSL
Top-1 Acc (Unseen)61.7
14
Showing 8 of 8 rows

Other info

Follow for update