Research map / Vision-language and multimodal / CLIP and zero-shot
Semantic-Enhanced Image Clustering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SIC with CLIP-guided semantic pseudo-labeling and joint image/semantic consistency learning | CLIP image clustering · STL10 | ACC: 80.9 -> 98.1 | Helped |
| Use SIC with CLIP-guided semantic pseudo-labeling and joint image/semantic consistency learning | CLIP image clustering · Cifar10 | ACC: 88.3 -> 92.7 | Helped |
| Use SIC with CLIP-guided semantic pseudo-labeling and joint image/semantic consistency learning | CLIP image clustering · Cifar100-20 | ACC: 50.7 -> 58.4 | Helped |
| Use SIC with CLIP-guided semantic pseudo-labeling and joint image/semantic consistency learning | CLIP image clustering · ImageNet-Dogs | ACC: 59.3 -> 71.3 | Helped |
| Use SIC with CLIP-guided semantic pseudo-labeling and joint image/semantic consistency learning | CLIP image clustering · Tiny-ImageNet | ACC: 42.0 -> 61.2 | Helped |
| Add image-semantic consistency learning loss (L_IS) (ablation) | SIC · Cifar10 | ACC: 84.4±0.5 -> 92.6±0.1 | Helped |
| Add image-neighbor consistency loss (L_I) (ablation) | SIC · Cifar10 | ACC: 71.2±0.1 -> 92.6±0.1 | Helped |
| Add balance regularization (L_B) (ablation) | SIC · Cifar10 | ACC: 70.3±7.2 -> 92.6±0.1 | Helped |
| Replace direct mapping with center-based mapping (ablation) | SIC · Cifar10 | ACC: 78.3{ ±0.1} -> 91.8{ ±0.1} | Helped |
| Adjust center-based semantic centers using nearest neighborhoods (ablation) | SIC · Cifar10 | ACC: 91.8{ ±0.1} -> 92.6{ ±0.1} | Helped |
| Use direct mapping instead of adjusted center-based mapping (ablation) | SIC · STL10 | ACC: 98.1{ ±0.1} -> 95.5{ ±0.1} | Hurt |
| Use center-based mapping without adjusting semantic centers (ablation) | SIC · STL10 | ACC: 98.1{ ±0.1} -> 96.7{ ±0.1} | Hurt |
Closest papers by meaning
- Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers (NeurIPS 2026 · similarity 0.90)
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models (ICLR 2024 · similarity 0.89)
- Image Clustering with External Guidance (ICML 2024 · similarity 0.88)
- Image Clustering Conditioned on Text Criteria (ICLR 2024 · similarity 0.88)
- RPSC: Robust Pseudo-Labeling for Semantic Clustering (AAAI 2024 · similarity 0.87)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.86)
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.