Research map / Detection and segmentation / CNN features
Large Scale Hard Sample Mining With Monte Carlo Tree Search
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 hierarchical MCTS sampling instead of uniform image sampling | ACF face detector · Face-free images, Boot3 | images visited: 10377 -> 5123 | Helped |
| Use hierarchical MCTS sampling instead of uniform image sampling | ACF face detector · Pascal Faces | AP: 84.4 -> 83.8 | No clear effect |
| Use hierarchical MCTS sampling instead of uniform image sampling | ACF face detector · AFW | AP: 95.3 -> 95.3 | No clear effect |
| Use MCTS sampling instead of uniform image sampling | ACF pedestrian detector · CaltechPedestrians, Boot3 | images visited: 13767 -> 8885 | Helped |
| Use MCTS sampling instead of uniform image sampling | ACF pedestrian detector · CaltechPedestrians test set | miss rate @ 0.1 fppi: 0.29 -> 0.30 | No clear effect |
| Use UCB1 with the win reward instead of uniform sampling (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 10377 -> 7811 | Helped |
| Use the normalized density reward with UCB1 instead of the win reward (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 7811 -> 7955 | No clear effect |
| Add GIST pre-clustering to Thompson-sampling MCTS (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 6627 -> 5123 | Helped |
| Add gradient pre-clustering to Thompson-sampling MCTS (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 6627 -> 5515 | Helped |
| Shuffle the hierarchical image grouping (ablation) | MCTS hard-sample mining · Face-free images, ACF, Boot3 | images visited: 6627 -> 9969 | Hurt |
| Add GIST pre-clustering to UCB1 with the win reward (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 7811 -> 4828 | Helped |
| Add GIST pre-clustering to UCB1 with the density reward (ablation) | ACF face detector · Face-free images, Boot3 | images visited: 7955 -> 5376 | Helped |
Closest papers by meaning
- Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection (CVPR 2018 · similarity 0.87)
- Query-Based Hard-Image Retrieval for Object Detection at Test Time (AAAI 2023 · similarity 0.87)
- MogFace: Towards a Deeper Appreciation on Face Detection (CVPR 2022 · similarity 0.86)
- Community Forensics: Using Thousands of Generators to Train Fake Image Detectors (CVPR 2025 · similarity 0.84)
- SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection (CVPR 2025 · similarity 0.83)
- Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes (AAAI 2024 · 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.