Research map / Label-efficient and robust learning / Recognition and long-tail
Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
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 |
|---|---|---|---|
| Add dynamic conceptional contrastive learning | GCD · CUB-200 | clustering accuracy (New): 48.7 -> 64.9 | Helped |
| Add dynamic conceptional contrastive learning | GCD · CIFAR10 | clustering accuracy (All): 91.5 -> 96.3 | Helped |
| Add dynamic conceptional contrastive learning | GCD · CIFAR100 | clustering accuracy (All): 73.0 -> 75.3 | Helped |
| Add dynamic conceptional contrastive learning | GCD · ImageNet-100 | clustering accuracy (All): 74.1 -> 80.5 | Helped |
| Add dynamic conceptional contrastive learning | GCD · Stanford-Cars | clustering accuracy (New): 29.9 -> 36.2 | Helped |
| Add dynamic conceptional contrastive learning | GCD · Oxford-Pet | clustering accuracy (All): 80.2 -> 88.1 | Helped |
| Add instance-level contrastive loss (ablation) | DCCL with conceptional losses, momentum update, and consolidation · CUB-200 | clustering accuracy (All): 60.1 -> 63.5 | Helped |
| Add instance-level contrastive loss (ablation) | DCCL with conceptional losses, momentum update, and consolidation · Oxford-Pet | clustering accuracy (All): 85.8 -> 88.1 | Helped |
| Add conception-level momentum update (ablation) | Conception-level contrastive learning · CUB-200 | clustering accuracy (New): 55.4 -> 58.1 | Helped |
| Add conception-level momentum update (ablation) | Conception-level contrastive learning · Oxford-Pet | clustering accuracy (All): 81.6 -> 83.5 | Helped |
| Add dispersion loss (ablation) | DCCL with conception-level loss and momentum update · CUB-200 | clustering accuracy (New): 58.1 -> 60.8 | Helped |
| Add conception consolidation (ablation) | DCCL with conception-level loss, dispersion loss, and momentum update · CUB-200 | clustering accuracy (All): 59.5 -> 60.1 | Helped |
Closest papers by meaning
- HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts (ICLR 2025 · similarity 0.88)
- Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery (AAAI 2025 · similarity 0.88)
- Towards Understanding Parametric Generalized Category Discovery on Graphs (ICML 2025 · similarity 0.88)
- SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery (NeurIPS 2025 · similarity 0.88)
- Federated Generalized Category Discovery (CVPR 2024 · similarity 0.88)
- Active Generalized Category Discovery (CVPR 2024 · similarity 0.87)
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.