DMAP: Decoupling-Driven Multi-Level Attribute Parsing for Interpretable Outfit Collocation
- 20 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 9988-10000
Abstract
Outfit collocation requires considering the interrelationship and adaptability among the attributes of component items. However, with the numerous and diverse attributes of fashion items, accurately capturing attribute features and modeling the complex relationships between attributes become the key challenges. To address these challenges, we propose a novel scheme Decoupling-driven Multi-level Attribute Parsing for interpretable outfit collocation. First, we decouple a series of attribute features from the item's visual feature by fully supervised, which can improve the robustness of the model in processing both relevant and irrelevant attributes of items. Furthermore, employing a deep deconvolution neural network with attention mechanisms to reconstruct the decoupled attribute features into a visual image that is close to the original item image. It ensures all attribute features can be combined to contain complete item information. Next, graph attention networks are constructed to parse multi-level attribute compatibility relationships from three perspectives: intra-attribute, inter-attribute, and item integration relationships. Finally, we use multi-layer perceptrons to fuse the score distributions of the three and output the outfit compatibility score. Experiments conducted on the IQON3000 dataset demonstrate that our model outperforms existing state-of-the-art methods and exhibits good interpretability.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFF0900900)
- National Natural Science Foundation of China (62172452)
This publication has 43 references indexed in Scilit:
- Personalized fashion outfit generation with user coordination preference learningInformation Processing & Management, 2023
- FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks2023
- Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis2023
- Learning Disentanglement with Decoupled Labels for Vision-Language Navigation2022
- FashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback2022
- Personalized Outfit Recommendation with Learnable Anchors2021
- Learning Binary Code for Personalized Fashion Recommendation2019
- Context-Aware Visual Compatibility Prediction2019
- Learning Type-Aware Embeddings for Fashion Compatibility2018
- Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences2015