Research map / Label-efficient and robust learning / Recognition and long-tail
Expert load matters: operating networks at high accuracy and low manual effort
Sara Sangalli, Ertunc Erdil, Ender Konukoglu
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 AUCOCL to cross-entropy | ResNet-50 · CIFAR100 | AUCOC: 91,10 -> 93,81 | Improved |
| Add AUCOCL to cross-entropy | ResNet-50 · CIFAR100 | accuracy: 73,69 -> 75,94 | Improved |
| Add AUCOCL to cross-entropy | ResNet-50 · CIFAR100 at 90% accuracy | τ₀: 34,72 -> 28,39 | Improved |
| Add AUCOCL to cross-entropy | WideResnet-28-10 · Tiny-ImageNet | AUCOC: 74,03 -> 76,64 | Improved |
| Add AUCOCL to cross-entropy | WideResnet-28-10 · Tiny-ImageNet | accuracy: 49,29 -> 51,40 | Improved |
| Add AUCOCL to cross-entropy | ResNet-50 · ImageNet | AUCOC: 36,04 -> 40,43 | Improved |
| Add AUCOCL to cross-entropy | ResNet-50 · ImageNet | accuracy: 20,19 -> 23,36 | Improved |
| Add AUCOCL to cross-entropy | ResNet-50 · SVHN OOD | AUROC: 81,64 -> 86,56 | Improved |
Closest papers by meaning
- Confidence-Aware Learning for Deep Neural Networks (ICML 2020 · similarity 0.84)
- Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs (ICML 2022 · similarity 0.84)
- Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach (ICML 2025 · similarity 0.83)
- Human Expertise in Algorithmic Prediction (NeurIPS 2024 · similarity 0.83)
- Mixture of Weak and Strong Experts on Graphs (ICLR 2024 · similarity 0.83)
- Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers (NeurIPS 2025 · similarity 0.83)
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.
