.png){kind=icon}
返回
DMAP: Decoupling-Driven Multi-Level Attribute Parsing for Interpretable Outfit Collocation
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2024.3402541.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Visualization
Feature extraction
Image reconstruction
Image color analysis
Deconvolution
Cotton
Matrix decomposition
Attribute parsing
graph attention network
image reconstruction
interpretability
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
Can CD34 discriminate between benign and malignant hepatocytic lesions in fine-needle aspirates and thin core biopsies?.png)
Cancer
OAAI
CancerIF0
OAAI分享收藏
COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion StylesCOutfitGAN: 学习合成由剪影面具和时尚风格监督的兼容服装
PREAI
分享收藏
查看更多内容