Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation
Shuili Zhang, Hongzhang Mu, Jiawei Sheng, Qianqian Tong, Wenyuan Zhang, Quangang Li, Tingwen Liu
Abstract
Attribute-specific fashion retrieval aims to enhance fine-grained image retrieval by emphasizing the similarity of specific attributes. Current methods primarily rely on attention mechanisms to extract attribute-related visual features but face two key challenges: the limitations of coarse-grained localization in achieving fine-grained accuracy, and an imbalance between global and local perception, where excessive focus on local features can undermine overall performance. To address these issues, we propose the fashion microscope ProFashion, which achieves pixel-level attribute awareness through optimal transport and neural semantic aggregation. The framework begins by employing optimal transport to align semantic attributes with visual patterns from a global perspective, generating an attribute-visual value map that highlights distinctive regions while reducing interference. This is followed by simulating the human brain
BibTeX
@inproceedings{aaai2026_fashionmicroscop,
title = {Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation},
author = {Shuili Zhang and Hongzhang Mu and Jiawei Sheng and Qianqian Tong and Wenyuan Zhang and Quangang Li and Tingwen Liu},
booktitle = {AAAI 2026},
year = {2026}
}