Research map / Label-efficient and robust learning / Recognition and long-tail
OpenAUC: Towards AUC-Oriented Open-Set Recognition
Zitai Wang, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang
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 the close-set correctness switch (OpenAUC coupling) to the AUC risk instead of plain Acc+AUC (ablation) | OpenAUC learning method · CIFAR10 | OpenAUC: 87.6 -> 89.2 | Improved |
| add the close-set correctness switch (OpenAUC coupling) to the AUC risk instead of plain Acc+AUC (ablation) | OpenAUC learning method · TinyImageNet | OpenAUC: 74.0 -> 75.9 | Improved |
| add the close-set correctness switch (OpenAUC coupling) to the AUC risk instead of plain Acc+AUC (ablation) | OpenAUC learning method · MNIST | OpenAUC: 99.3 -> 99.4 | Improved |
| add the close-set correctness switch (OpenAUC coupling) to the AUC risk instead of plain Acc+AUC (ablation) | OpenAUC learning method · CIFAR+50 | OpenAUC: 92.0 -> 93.6 | Improved |
| replace CE+ training with OpenAUC risk optimization | VGG32 CE+ · TinyImageNet | OpenAUC: 74.3 -> 75.9 | Improved |
| replace CE+ training with OpenAUC risk optimization | VGG32 CE+ · CIFAR10 | OpenAUC: 88.1 -> 89.2 | Improved |
| replace Softmax with OpenAUC risk optimization | VGG32 · SVHN | OpenAUC: 92.8 -> 95.0 | Improved |
| replace CE+ with OpenAUC risk optimization | ResNet50 on CUB · CUB Hard | AUC: 76.3 -> 78.1 | Improved |
| replace CE+ with OpenAUC risk optimization | ResNet50 on CUB · CUB close-set | close-set accuracy: 86.2 -> 86.2 | No clear effect |
| increase lambda weight of AUC risk beyond 0.1-0.2 (ablation) | OpenAUC learning method · benchmarks (Fig sensitivity) | OpenAUC | Hurt |
Closest papers by meaning
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.92)
- The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition (ICLR 2023 · similarity 0.90)
- Operational Open-Set Recognition and PostMax Refinement (ECCV 2024 · similarity 0.89)
- OpenGAN: Open-Set Recognition via Open Data Generation (ICCV 2021 · similarity 0.89)
- From Coarse to Fine-Grained Open-Set Recognition (CVPR 2024 · similarity 0.88)
- All Beings Are Equal in Open Set Recognition (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.
