Research map / Label-efficient and robust learning / Recognition and long-tail
Reliable Confidence Alignment for Generalized Category Discovery
Jiawei Yu, Zijian Gao, Tianjiao Wan, Xuan Liu, Cheng Yang, Kele Xu
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 RAC (Dirichlet certainty anchoring on labeled data) (ablation) | SimGCD · CUB | Old accuracy: 67.38 -> 71.58 | Improved |
| add RAC (ablation) | SimGCD · CIFAR100 | All accuracy: 79.43 -> 82.46 | Improved |
| add CCA on top of RAC (ablation) | SimGCD · CUB | Old accuracy: 71.58 -> 72.38 | Improved |
| add CCA on top of RAC (ablation) | SimGCD · CIFAR100 | New accuracy: 82.65 -> 82.18 | Hurt |
| add CCA on top of RAC (ablation) | SimGCD · CIFAR100 | All accuracy: 82.46 -> 82.85 | Improved |
| add RAC (ablation) | AFGCD · CUB | All accuracy: 69.66 -> 70.73 | Improved |
| add CCA on top of RAC (ablation) | AFGCD · CUB | All accuracy: 70.73 -> 71.20 | Improved |
| use Exp(Tanh) evidence instead of Softplus (ablation) | RCA on SimGCD · FGVC-Aircraft | All accuracy: 55.87 -> 56.79 | Improved |
| use Exp(Tanh) evidence instead of Exp (ablation) | RCA on SimGCD · Stanford Cars | All accuracy: 55.26 -> 55.55 | Improved |
| increase RAC weight lambda1 from 0.1 to 0.7 (ablation) | RCA · CUB and FGVC-Aircraft | New accuracy | Hurt |
| vary CCA weight lambda2 from 0.1 to 0.7 (ablation) | RCA · CUB | All accuracy: varies by only 0.1% | No clear effect |
| add RCA to SimGCD on CIFAR10 | SimGCD · CIFAR10 | All accuracy: 97.0 -> 97.1 | No clear effect |
Closest papers by meaning
- Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery (NeurIPS 2025 · similarity 0.89)
- Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective (ICML 2025 · similarity 0.88)
- Transfer and Alignment Network for Generalized Category Discovery (AAAI 2024 · similarity 0.87)
- Happy: A Debiased Learning Framework for Continual Generalized Category Discovery (NeurIPS 2024 · similarity 0.87)
- Unleashing the Potential of Model Bias for Generalized Category Discovery (AAAI 2025 · similarity 0.85)
- Solving the Catastrophic Forgetting Problem in Generalized Category Discovery (CVPR 2024 · 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.
