AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

Yuying Ge, Ruimao Zhang, Xiaogang Wang, Xiaoou Tang, Ping Luo

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 357 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
Combine pose and class features for retrieval rather than using class features alone (ablation)Match R-CNN · DeepFashion2 validation retrieval, ground-truth boxestop-1 accuracy: 0.122 -> 0.268Improved
Combine pose and class features for retrieval rather than using class features alone (ablation)Match R-CNN · DeepFashion2 validation retrieval, detected boxestop-20 accuracy: 0.417 -> 0.617Improved
Combine pose and class features rather than mask and class features (ablation)Match R-CNN · DeepFashion2 validation retrieval, ground-truth boxestop-1 accuracy: 0.214 -> 0.268Improved
Combine pose and class features rather than mask and class features (ablation)Match R-CNN · DeepFashion2 validation retrieval, detected boxestop-20 accuracy: 0.564 -> 0.617Improved
Use ground-truth boxes instead of detected boxesMatch R-CNN retrieval · DeepFashion2 validationtop-20 accuracy: 0.617 -> 0.665Improved
Evaluate landmark AP on visible and occluded landmarks rather than visible landmarks onlyMask R-CNN · DeepFashion2 validation, overallAP_pt: 0.641 -> 0.563Hurt
Use pose features rather than mask features for retrieval (ablation)Match R-CNN · DeepFashion2 validation retrieval, ground-truth boxestop-1 accuracy: 0.187 -> 0.255Improved
Use pose features rather than mask features for retrieval (ablation)Match R-CNN · DeepFashion2 validation retrieval, detected boxestop-20 accuracy: 0.529 -> 0.589Improved
Evaluate detection on heavily occluded rather than slightly occluded itemsMask R-CNN · DeepFashion2 validationAP_box: 0.712 -> 0.372Hurt
Evaluate detection on large zoom-in rather than no zoom-in itemsMask R-CNN · DeepFashion2 validationAP_box: 0.695 -> 0.466Hurt
Evaluate segmentation on heavily occluded rather than slightly occluded itemsMask R-CNN · DeepFashion2 validationAP_mask: 0.720 -> 0.389Hurt
Evaluate landmark estimation on heavily occluded rather than slightly occluded itemsMask R-CNN · DeepFashion2 validation, visible landmarksAP_pt: 0.669 -> 0.398Hurt

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