Research map / Label-efficient and robust learning / Recognition and long-tail
Adversarial Reciprocal Points Learning for Open Set Recognition
Guangyao Chen, Peixi Peng, Xiangqian Wang, Yonghong Tian
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 confusing samples with adversarial BN and fine-tuning to ARPL | ARPL · TinyImageNet (open set) | OSCR: 62.3 -> 65.9 | Improved |
| add confusing samples to ARPL | ARPL · TinyImageNet (open set) | AUROC: 76.2 -> 78.2 | Improved |
| use ARPL instead of RPL | RPL · CIFAR+10 (open set) | AUROC: 84.2 -> 96.5 | Improved |
| use ARPL instead of RPL | RPL · CIFAR10 (open set) | AUROC: 82.7 -> 90.1 | Improved |
| use ARPL instead of softmax cross-entropy | softmax · TinyImageNet (open set) | OSCR: 60.8 -> 62.3 | Improved |
| use GCPL prototypes instead of softmax | softmax · TinyImageNet (open set) | OSCR: 60.8 -> 59.3 | Hurt |
| add adversarial batch norm (ABN) to ARPL+CS (ablation) | ARPL+CS · OOD CIFAR10 vs SVHN | AUROC: 90.9 -> 96.6 | Improved |
| add fine-tuning (FT) to ARPL+CS (ablation) | ARPL+CS · OOD CIFAR10 vs SVHN | AUROC: 95.6 -> 96.6 | Improved |
| add fine-tuning (FT) to ARPL+CS (ablation) | ARPL+CS · OOD CIFAR10 vs CIFAR100 | AUROC: 89.7 -> 90.3 | Improved |
| add adversarial batch norm (ABN) to ARPL+CS (ablation) | ARPL+CS · OOD CIFAR10 vs CIFAR100 | AUROC: 88.8 -> 90.3 | Improved |
| add FT to ARPL+CS (ablation) | ARPL+CS · CIFAR100 (closed set) | accuracy: 71.5 -> 72.8 | Improved |
| add ABN to ARPL+CS (ablation) | ARPL+CS · CIFAR100 (closed set) | accuracy: 71.8 -> 72.8 | Improved |
Closest papers by meaning
- Learning Open Set Network with Discriminative Reciprocal Points (ECCV 2020 · similarity 0.93)
- All Beings Are Equal in Open Set Recognition (AAAI 2024 · similarity 0.87)
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.87)
- Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition (AAAI 2025 · similarity 0.86)
- Frequency Shuffling and Enhancement for Open Set Recognition (AAAI 2024 · similarity 0.84)
- Exploring Diverse Representations for Open Set Recognition (AAAI 2024 · similarity 0.84)
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.
