Research map / Detection and segmentation / CNN features
Imbalance Problems in Object Detection: A Review
Kemal Öksüz, Barış Can Çam, Sinan Kalkan, Emre Akbaş
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 |
|---|---|---|---|
| replace alpha-balanced cross entropy with Focal Loss | RetinaNet · MS COCO 2017 minival | mAP: 31.1 to 34.0 | Improved |
| replace Focal Loss with AP Loss | RetinaNet · MS COCO 2017 minival | mAP: 33.9 to 35.0 | Improved |
| add OHEM hard example mining | Fast R-CNN VGG-16 · MS COCO 2015 | mAP: 14.7% | Improved |
| add prime sample attention for positives | detector with sampling · MS COCO 2017 minival | mAP: 36.4 to 38.0 | Improved |
Closest papers by meaning
- Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels (CVPR 2020 · similarity 0.86)
- Large-Scale Object Detection in the Wild With Imbalanced Data Distribution, and Multi-Labels (TPAMI 2024 · similarity 0.86)
- Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection (ICCV 2023 · similarity 0.86)
- Unbalanced Optimal Transport: A Unified Framework for Object Detection (CVPR 2023 · similarity 0.85)
- Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection (ICML 2024 · similarity 0.84)
- DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model (NeurIPS 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.
