Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11050-11059
Abstract
Fashion representation learning involves the analysis and understanding of various visual elements at different granularities and the interactions among them. Existing works often learn fine-grained fashion representations at the attribute level without considering their relationships and inter-dependencies across different classes. In this work, we propose to learn an attribute and class-specific fashion representation duet to better model such attribute relationships and inter-dependencies by leveraging prior knowledge about the taxonomy of fashion attributes and classes. Through two sub-networks for the attributes and classes, respectively, our proposed an embedding network progressively learns and refines the visual representation of a fashion image to improve its robustness for fashion retrieval. A multi-granularity loss consisting of attribute-level and class-level losses is proposed to introduce appropriate inductive bias to learn across different granularities of the fashion representations. Experimental results on three benchmark datasets demonstrate the effectiveness of our method, which outperforms the state-of-the-art methods by a large margin.Keywords
This publication has 23 references indexed in Scilit:
- Clothing retrieval with visual attention model2017
- Automatic Spatially-Aware Fashion Concept Discovery2017
- Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search2017
- Conditional Similarity Networks2017
- Learning Compatibility Across Categories for Heterogeneous Item Recommendation2016
- Deep Residual Learning for Image Recognition2016
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations2016
- Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences2015
- Image-Based Recommendations on Styles and Substitutes2015
- ImageNet: A large-scale hierarchical image database2009