Research map / Detection and segmentation / Open-set and few-shot detection
Power Battery Detection
Xiaoqi Zhao, Peiqian Cao, Chenyang Yu, Zonglei Feng, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Youwei Pang, Jinsong Ouyang, Weisi Lin, Georges El Fakhri, Huchuan Lu and 1 more
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 |
|---|---|---|---|
| use intelligent annotation pipeline instead of manual annotation | PBD5K labeling · PBD5K annotation | annotation time (min/image): 3.4 -> 1.2 | Improved |
| use intelligent annotation pipeline instead of manual annotation | PBD5K labeling · PBD5K annotation | spatial deviation (pixel): 3.5 -> 0.9 | Improved |
| use intelligent annotation pipeline instead of manual annotation | PBD5K labeling · PBD5K annotation | rework rate: 17% -> 6% | Improved |
| upgrade MDCNet to MDCNeXt with prompt-filtered and density-aware reordering state space modules | MDCNet · PBD5K average | AN-ACC: 0.7392 -> 0.8705 | Improved |
| upgrade MDCNet to MDCNeXt | MDCNet · PBD5K average | PN-ACC: 0.6416 -> 0.7705 | Improved |
| upgrade MDCNet to MDCNeXt | MDCNet · PBD5K average | OH-MAE: 3.7732 -> 1.0667 | Improved |
| model PBD as point segmentation instead of tiny object detection (HS-FPN) | HS-FPN · PBD5K average | AN-ACC: 0.5222 -> 0.8705 | Improved |
| model PBD as point segmentation instead of tiny object detection (HS-FPN) | HS-FPN · PBD5K average | AL-MAE: 9.8354 -> 1.2617 | Improved |
| use MDCNeXt instead of ZoomNeXt for segmentation | ZoomNeXt · PBD5K average | mIoU: 0.6290 -> 0.7458 | Improved |
| use prompt-based generalist SAM 2 with pure battery prompts instead of training on PBD5K | SAM 2 · PBD5K average | mDice: 0.1421 vs 0.6489 (MDCNeXt) | Hurt |
| move from regular to tough split | MDCNeXt · PBD5K | AN-ACC: 0.9379 -> 0.7873 | Hurt |
| evaluate PN-ACC at plate level instead of sample level | MDCNeXt · PBD5K tough split | PN-ACC: 0.6263 -> 96% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ZoomNeXt — ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline (CVPR 2024 · similarity 0.83)
- CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset (NeurIPS 2024 · similarity 0.81)
- BatteryML: An Open-source Platform for Machine Learning on Battery Degradation (ICLR 2024 · similarity 0.80)
- Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection (AAAI 2024 · similarity 0.79)
- MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images (ICLR 2024 · similarity 0.79)
- 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly Detection (AAAI 2025 · similarity 0.78)
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.
