Deep Fashion Analysis with Feature mAP Upsampling and Landmark-Driven Attention

Abstract

In this paper, we propose an attentive fashion network to address three problems of fashion analysis, namely landmark localization, category classification and attribute prediction. By utilizing a landmark prediction branch with upsampling network structure, we boost the accuracy of fashion landmark localization. With the aid of the predicted landmarks, a landmark-driven attention mechanism is proposed to help improve the precision of fashion category classification and attribute prediction. Experimental results show that our approach outperforms the state-of-the-arts on the DeepFashion dataset.

Cite

Text

Liu and Lu. "Deep Fashion Analysis with Feature mAP Upsampling and Landmark-Driven Attention." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11015-4_4

Markdown

[Liu and Lu. "Deep Fashion Analysis with Feature mAP Upsampling and Landmark-Driven Attention." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/liu2018eccvw-deep-a/) doi:10.1007/978-3-030-11015-4_4

BibTeX

@inproceedings{liu2018eccvw-deep-a,
  title     = {{Deep Fashion Analysis with Feature mAP Upsampling and Landmark-Driven Attention}},
  author    = {Liu, Jingyuan and Lu, Hong},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {30-36},
  doi       = {10.1007/978-3-030-11015-4_4},
  url       = {https://mlanthology.org/eccvw/2018/liu2018eccvw-deep-a/}
}