Research map / Detection and segmentation / Open-set and few-shot detection
Computing the Testing Error Without a Testing Set
Ciprian A. Corneanu, Sergio Escalera, Aleix M. Martinez
Check 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 |
|---|---|---|---|
| use life and midlife together instead of life alone (ablation) | Topology estimator · Object recognition | test-performance estimation error (%): 11.86±7.39 -> 8.45±5.85 | Improved |
| use life and midlife together instead of midlife alone (ablation) | Topology estimator · Object recognition | test-performance estimation error (%): 9.89±6.65 -> 8.45±5.85 | Improved |
| use life and midlife together instead of life alone (ablation) | Topology estimator · AU recognition | test-performance estimation error (%): 6.62±4.08 -> 5.52±3.62 | Improved |
| use life and midlife together instead of midlife alone (ablation) | Topology estimator · AU recognition | test-performance estimation error (%): 3.83±3.58 -> 5.52±3.62 | Hurt |
| use life and midlife together instead of life alone (ablation) | Topology estimator · Semantic segmentation | test-performance estimation error (%): 5.43±4.24 -> 4.60±3.11 | Improved |
| use life and midlife together instead of midlife alone (ablation) | Topology estimator · Semantic segmentation | test-performance estimation error (%): 7.07±4.08 -> 4.60±3.11 | Improved |
| use a nonlinear regressor instead of the linear mapping (ablation) | Topology estimator · computer vision tasks | test-performance estimation error | Improved |
| use a nonlinear regressor instead of the linear mapping (ablation) | Topology estimator · less common network topologies | generalization to network topologies | Hurt |
Closest papers by meaning
- Reducing Flipping Errors in Deep Neural Networks (AAAI 2022 · similarity 0.86)
- MEMO: Test Time Robustness via Adaptation and Augmentation (NeurIPS 2022 · similarity 0.86)
- Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels (ICML 2019 · similarity 0.86)
- Model Similarity Mitigates Test Set Overuse (NeurIPS 2019 · similarity 0.85)
- ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object (CVPR 2024 · similarity 0.84)
- Online GNN Evaluation Under Test-time Graph Distribution Shifts (ICLR 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.
