Research map / Detection and segmentation / CNN features
CrossDet: Crossline Representation for Object Detection
Heqian Qiu, Hongliang Li, Qingbo Wu, Jianhua Cui, Zichen Song, Lanxiao Wang, Minjian Zhang
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 crossline representation instead of center points | CrossDet two-stage · PASCAL VOC2007 test | AP: 48.4 -> 50.9 | Improved |
| use crossline representation instead of key points | CrossDet two-stage · PASCAL VOC2007 test | AP: 48.9 -> 50.9 | Improved |
| use crossline representation instead of anchor boxes | CrossDet two-stage · PASCAL VOC2007 test | AP: 49.3 -> 50.9 | Improved |
| add crossline extraction module (ablation) | CrossDet · PASCAL VOC2007 test | AP: 48.4 -> 50.9 | Improved |
| add axis-aware average pooling (ablation) | CrossDet CEM · PASCAL VOC2007 test | AP: 50.5 -> 50.9 | Improved |
| use global average pooling instead of none (ablation) | CrossDet CEM · PASCAL VOC2007 test | AP: 50.5 -> 50.5 | No clear effect |
| add soft-weighted crossline sampling (ablation) | CrossDet CEM · PASCAL VOC2007 test | AP: 48.8 -> 50.9 | Improved |
| use soft-weighted instead of max sampling (ablation) | CrossDet CEM · PASCAL VOC2007 test | AP: 50.7 -> 50.9 | Improved |
| add CEM to the classification branch only (ablation) | CrossDet · PASCAL VOC2007 test | AP: 48.4 -> 49.4 | Improved |
| add CEM to the regression branch only (ablation) | CrossDet · PASCAL VOC2007 test | AP: 48.4 -> 49.5 | Improved |
| add CEM on both branches (ablation) | CrossDet · PASCAL VOC2007 test | AP: 49.5 -> 50.9 | Improved |
| add decoupled regression (ablation) | CrossDet · PASCAL VOC2007 test | AP: 50.1 -> 50.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 2 shared results
- BorderDet* — BorderDet: Border Feature for Dense Object Detection (ECCV 2020) · better on 1 of 1 shared result
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
- OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-Shot Unsupervised Image-to-Image Translation (AAAI 2022 · similarity 0.87)
- Unbiased Mean Teacher for Cross-Domain Object Detection (CVPR 2021 · similarity 0.87)
- Dual Instance-Consistent Network for Cross-Domain Object Detection (TPAMI 2022 · similarity 0.87)
- MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer (ECCV 2022 · similarity 0.86)
- CrossKD: Cross-Head Knowledge Distillation for Object Detection (CVPR 2024 · similarity 0.85)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.85)
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.
