AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition

Yuwei Zhang, Peng Zhang, Chun Yuan, Zhi Wang

CVPR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 53 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add landmark joint learning (ablation)VGG16 clothing classifier and attribute recognizer · DeepFashion-Ccategory top-3 accuracy: 89.94 -> 91.54Improved
Add landmark joint learning (ablation)VGG16 attribute recognizer · DeepFashion-C, shape attributestop-3 recall: 60.03 -> 61.70Improved
Use ImageNet pre-training (ablation)VGG16 attribute recognizer · DeepFashion-C, texture attributestop-3 recall: 55.73 -> 58.34Improved
Use ImageNet pre-training (ablation)VGG16 attribute recognizer · DeepFashion-C, shape attributestop-3 recall: 60.03 -> 60.41No clear effect
Add landmark-aware attention to landmark joint learning (ablation)VGG16 clothing classifier · DeepFashion-Ccategory top-3 accuracy: 91.59 -> 91.56No clear effect
Combine landmark joint learning and ImageNet pre-training in one stream (ablation)VGG16 attribute recognizer · DeepFashion-Call-attribute top-3 recall: 49.23 -> 48.77Hurt
Separate texture-biased and shape-biased features into two streams (ablation)VGG16 attribute recognizer · DeepFashion-Call-attribute top-3 recall: 48.77 -> 50.58Improved
Jointly train category classification and attribute recognition (ablation)VGG16 multitask model · DeepFashion-Ccategory top-3 accuracy: 87.64 -> 89.94Improved
Jointly train category classification and attribute recognition (ablation)VGG16 multitask model · DeepFashion-C, shape attributestop-3 recall: 58.50 -> 60.03Improved
Add landmark joint learning (ablation)clothing retrieval attribute recognizer · In-shop Clothes Retrievaltop-30 recall: 75.29 -> 75.33No clear effect
Add landmark joint learning (ablation)clothing retrieval attribute recognizer · Consumer-to-Shop Clothes Retrievaltop-20 recall: 65.29 -> 68.42Improved
Use the proposed two-stream TS-FashionNetclothing classifier and attribute recognizer · DeepFashion-C testall-attribute top-3 recall: 49.19 -> 50.58Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy