Research map / Label-efficient and robust learning / Recognition and long-tail
Twin Contrastive Learning for Online Clustering
Yunfan Li, Mouxing Yang, Dezhong Peng, Taihao Li, Jiantao Huang, Xi Peng
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 |
|---|---|---|---|
| add self-labeling boosting loss (ablation) | TCL · CIFAR-10 | ACC: 0.865 -> 0.878 | Improved |
| add self-supervised contrastive loss to boosting (SL+SCL) (ablation) | TCL · CIFAR-10 | ACC: 0.878 -> 0.887 | Improved |
| add the confidence-based boosting stage (ablation) | TCL · ImageNet-1K | ACC: 0.3160 -> 0.3789 | Improved |
| add instance-level contrastive head (ablation) | TCL · CIFAR-10 | ACC: 0.658 -> 0.865 | Improved |
| add cluster-level contrastive head (ablation) | TCL · CIFAR-10 | ACC: 0.821 -> 0.865 | Improved |
| add cluster-level contrastive head (ablation) | TCL · StackOverflow | ACC: 0.732 -> 0.860 | Improved |
| add decoupling of instance and cluster heads (ablation) | TCL · CIFAR-10 | ACC: 0.640 -> 0.854 | Improved |
| add decoupling of instance and cluster heads (ablation) | TCL · ImageNet-Dogs | ACC: 0.368 -> 0.535 | Improved |
| use weak+strong instead of weak+weak augmentation (ablation) | TCL · CIFAR-10 | ACC: 0.805 -> 0.865 | Improved |
| use weak+strong instead of strong+strong augmentation (ablation) | TCL · ImageNet-Dogs | ACC: 0.147 -> 0.549 | Improved |
| use mixed weak+strong augmentation for SimCLR+k-means (ablation) | SimCLR+k-means · CIFAR-10 | ACC: 0.782 -> 0.821 (+0.039) | Improved |
| increase ICH dimension from 10 to 64 (ablation) | TCL · CIFAR-10 | ACC: 0.854 -> 0.871 | Improved |
Closest papers by meaning
- 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)
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.86)
- Contrastive Multi-view Subspace Clustering via Tensor Transformers Autoencoder (AAAI 2025 · similarity 0.86)
- Partial Multi-View Clustering via Self-Supervised Network (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.
