Research map / Label-efficient and robust learning / Self-supervised and contrastive
You Never Cluster Alone
Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip Torr, Ling Shao
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 |
|---|---|---|---|
| remove cluster-level contrastive loss L1 (ablation) | TCC · CIFAR-10 | ACC: 90.6 -> 78.7 | Hurt |
| remove instance-level loss L2, keep only L1 (ablation) | TCC · CIFAR-10 | ACC: 90.6 -> 45.4 | Hurt |
| sample 10 Gumbel softmax latents instead of one (ablation) | TCC · CIFAR-10 | ACC: 90.6 -> 90.1 | No clear effect |
| remove cluster-level memory bank P and use K-1 other clusters as negatives (ablation) | TCC · CIFAR-10 | ACC: 90.6 -> 82.9 | Hurt |
| add cluster-level augmentation for L1 (ablation) | TCC · CIFAR-10 | ACC: 85.3 -> 90.6 | Improved |
| use soft assignments rather than hard assignments for cluster aggregation (ablation) | TCC · CIFAR-10 | ACC: 79.2 -> 90.6 | Improved |
| use end-to-end batch training instead of alternating epoch-wise training (ablation) | TCC · CIFAR-10 | ACC: 80.0 -> 90.6 | Improved |
| add cluster-level representations over MiCE instance-only model | TCC · CIFAR-10 | ACC: 83.5 -> 90.6 | Improved |
| TCC versus CC | TCC · STL-10 | ACC: 85.0 -> 81.4 | Hurt |
| TCC versus CC | TCC · Tiny ImageNet | ACC: 14.0 -> 30.6 | Improved |
| TCC versus SwAV re-implemented with same backbone | TCC · CIFAR-10 | ACC: 79.6 -> 90.6 | Improved |
| larger loss weight alpha for L1 | TCC · CIFAR-10 | ACC | No clear effect |
Closest papers by meaning
- Partial Multi-View Clustering via Self-Supervised Network (AAAI 2024 · similarity 0.87)
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.87)
- Multi-view Granular-ball Contrastive Clustering (AAAI 2025 · similarity 0.87)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.87)
- Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering (NeurIPS 2025 · similarity 0.86)
- Clustering Properties of Self-Supervised Learning (ICML 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.
