Research map / Detection and segmentation / Open-set and few-shot detection
Learning To Predict Visual Attributes in the Wild
Khoi Pham, Kushal Kafle, Zhe Lin, Zhihong Ding, Scott Cohen, Quan Tran, Abhinav Shrivastava
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add negative label expansion (ablation) | Strong Baseline · VAW test | mAP: 65.9 -> 67.7 | Improved |
| Add supervised contrastive learning after negative label expansion (ablation) | Strong Baseline · VAW test | mAP: 67.7 -> 68.2 | Improved |
| Add reweighting and repeat factor sampling after negative expansion and SupCon (ablation) | Strong Baseline · VAW test | mR@15: 55.2 -> 58.3 | Improved |
| Apply SCoNE (ablation) | ResNet-Baseline · VAW test | mAP: 63.0 -> 66.4 | Improved |
| Add multi-attention (ablation) | Strong Baseline · VAW test | mAP: 67.4 -> 67.7 | Improved |
| Add low-level features (ablation) | Strong Baseline · VAW test | mAP: 67.3 -> 67.7 | Improved |
| Add the object localizer (ablation) | Strong Baseline · VAW test | mAP: 66.9 -> 67.7 | Improved |
| Add object localizer, multi-attention, and low-level features (ablation) | ResNet-Baseline · VAW test | mAP: 65.6 -> 67.7 | Improved |
| Use SupCon pretraining instead of joint SupCon training (ablation) | Strong Baseline with multi-attention · VAW test | mAP: 67.7 -> 67.3 | Hurt |
| Jointly train with SupCon loss (ablation) | Strong Baseline with multi-attention · VAW test | mAP: 67.7 -> 68.2 | Improved |
| Use SupCon pretraining without multi-attention (ablation) | Strong Baseline without multi-attention · VAW test | mAP: 67.4 -> 67.6 | Improved |
| Use class-aware sampling (ablation) | ResNet-Baseline after negative label expansion · VAW test | mAP: 65.6 -> 63.5 | Hurt |
Closest papers by meaning
- Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework (TPAMI 2018 · similarity 0.89)
- Submodular Attribute Selection for Visual Recognition (TPAMI 2016 · similarity 0.89)
- OW-VAP: Visual Attribute Parsing for Open World Object Detection (ICML 2025 · similarity 0.86)
- Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent (NeurIPS 2025 · similarity 0.86)
- Detecting Open World Objects via Partial Attribute Assignment (CVPR 2025 · similarity 0.86)
- Compositional Caching for Training-free Open-vocabulary Attribute Detection (CVPR 2025 · similarity 0.85)
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.
