Research map / Label-efficient and robust learning / Recognition and long-tail
CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering
Shuai Shen, Wanhua Li, Xiaobing Wang, Dafeng Zhang, Zhezhu Jin, Jie Zhou, Jiwen Lu
Read the paperCheck 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 |
|---|---|---|---|
| use neighbor-aware cross-attention fusion instead of averaging hallucinated features (ablation) | CLIP-Cluster proxy generator · MS1M Part1 | Pairwise F-score: 93.76 -> 94.22 | Improved |
| use neighbor-aware cross-attention instead of self-attention (ablation) | CLIP-Cluster proxy generator · MS1M Part1 | Pairwise F-score: 94.04 -> 94.22 | Improved |
| add Infomap graph refinement instead of naive pruning (ablation) | CLIP-Cluster inference · MS1M Part1 | Pairwise F-score: 88.86 -> 94.22 | Improved |
| add attribute hallucination and proxy generator on top of Infomap (ablation) | Infomap clustering · MS1M Part1 | Pairwise F-score: 93.98 -> 94.22 | Improved |
| use CLIP-Cluster instead of ADA-Nets on larger test sets | face clustering · MS1M 5.21M unlabeled | Pairwise F-score: 83.99 -> 87.99 | Improved |
| use CLIP-Cluster pseudo-labels for face recognition training | face recognition on MegaFace · MegaFace rank-1, 1M distractors | rank-1 accuracy (%): 58.2% -> 80.5% | Improved |
| use CLIP-Cluster instead of STAR-FC++ | face clustering · MS1M Part1 | inference time: 312s -> 280s | Improved |
Closest papers by meaning
- Structure-Aware Face Clustering on a Large-Scale Graph With 107 Nodes (CVPR 2021 · similarity 0.86)
- On Mitigating Hard Clusters for Face Clustering (ECCV 2022 · similarity 0.86)
- Linkage Based Face Clustering via Graph Convolution Network (CVPR 2019 · similarity 0.85)
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models (ICLR 2024 · similarity 0.85)
- SegFace: Face Segmentation of Long-Tail Classes (AAAI 2025 · similarity 0.84)
- MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation (CVPR 2024 · similarity 0.83)
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.
