AI Paper Atlas

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

IJCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
use intelligent annotation pipeline instead of manual annotationPBD5K labeling · PBD5K annotationannotation time (min/image): 3.4 -> 1.2Improved
use intelligent annotation pipeline instead of manual annotationPBD5K labeling · PBD5K annotationspatial deviation (pixel): 3.5 -> 0.9Improved
use intelligent annotation pipeline instead of manual annotationPBD5K labeling · PBD5K annotationrework rate: 17% -> 6%Improved
upgrade MDCNet to MDCNeXt with prompt-filtered and density-aware reordering state space modulesMDCNet · PBD5K averageAN-ACC: 0.7392 -> 0.8705Improved
upgrade MDCNet to MDCNeXtMDCNet · PBD5K averagePN-ACC: 0.6416 -> 0.7705Improved
upgrade MDCNet to MDCNeXtMDCNet · PBD5K averageOH-MAE: 3.7732 -> 1.0667Improved
model PBD as point segmentation instead of tiny object detection (HS-FPN)HS-FPN · PBD5K averageAN-ACC: 0.5222 -> 0.8705Improved
model PBD as point segmentation instead of tiny object detection (HS-FPN)HS-FPN · PBD5K averageAL-MAE: 9.8354 -> 1.2617Improved
use MDCNeXt instead of ZoomNeXt for segmentationZoomNeXt · PBD5K averagemIoU: 0.6290 -> 0.7458Improved
use prompt-based generalist SAM 2 with pure battery prompts instead of training on PBD5KSAM 2 · PBD5K averagemDice: 0.1421 vs 0.6489 (MDCNeXt)Hurt
move from regular to tough splitMDCNeXt · PBD5KAN-ACC: 0.9379 -> 0.7873Hurt
evaluate PN-ACC at plate level instead of sample levelMDCNeXt · PBD5K tough splitPN-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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy