Research map / Detection and segmentation / Open-set and few-shot detection
Learning Loss for Active Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 predicted target losses to select examples for annotation instead of entropy-based sampling | ResNet-18 · CIFAR-10 | accuracy: 0.9059 -> 0.9101 | Helped |
| Use predicted target losses to select examples for annotation instead of core-set sampling | ResNet-18 · CIFAR-10 | accuracy: 0.9010 -> 0.9101 | Helped |
| Use predicted target losses to select examples for annotation instead of random sampling | ResNet-18 · CIFAR-10 | accuracy: 0.8764 -> 0.9101 | Helped |
| Use predicted target losses to select examples for annotation instead of entropy-based sampling | SSD (VGG-16) · PASCAL VOC 2007+2012 | mAP: 0.7222 -> 0.7338 | Helped |
| Use predicted target losses to select examples for annotation instead of core-set sampling | SSD (VGG-16) · PASCAL VOC 2007+2012 | mAP: 0.7171 -> 0.7338 | Helped |
| Use predicted target losses to select examples for annotation instead of random sampling | SSD (VGG-16) · PASCAL VOC 2007+2012 | mAP: 0.7117 -> 0.7338 | Helped |
| Use predicted target losses to select examples for annotation instead of entropy-based sampling | Stacked Hourglass (2 stacks) · MPII | PCKh@0.5: 0.7899 -> 0.8046 | Helped |
| Use predicted target losses to select examples for annotation instead of core-set sampling | Stacked Hourglass (2 stacks) · MPII | PCKh@0.5: 0.7985 -> 0.8046 | Helped |
| Use predicted target losses to select examples for annotation instead of random sampling | Stacked Hourglass (2 stacks) · MPII | PCKh@0.5: 0.7862 -> 0.8046 | Helped |
| Replace pairwise ranking loss with MSE loss for the loss prediction module (ablation) | Learn loss · CIFAR-10 | accuracy | Hurt |
Closest papers by meaning
- A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles (ICLR 2023 · similarity 0.86)
- Deep Active Learning with a Neural Architecture Search (NeurIPS 2019 · similarity 0.86)
- Active Learning for Convolutional Neural Networks: A Core-Set Approach (ICLR 2018 · similarity 0.86)
- Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection (CVPR 2022 · similarity 0.85)
- Training Deep Neural Networks via Direct Loss Minimization (ICML 2016 · similarity 0.85)
- Active Learning Guided by Efficient Surrogate Learners (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.