Research map / Detection and segmentation / Weakly supervised detection and segmentation
Few-Example Object Detection with Model Communication
Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng
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 |
|---|---|---|---|
| add multi-modal learning to Fast R-CNN VGG16 (ablation) | self-paced Fast R-CNN · PASCAL VOC 2007 test | mAP: 33.7 -> 36.0 | Improved |
| add multi-modal learning to R-FCN ResNet50 ohem (ablation) | self-paced R-FCN · PASCAL VOC 2007 test | mAP: 29.9 -> 37.4 | Improved |
| add multi-modal learning to R-FCN ResNet101 (ablation) | self-paced R-FCN · PASCAL VOC 2007 test | mAP: 31.4 -> 38.3 | Improved |
| combine three detectors with multi-modal learning instead of late-fusion ensemble | SPL+Ensemble · PASCAL VOC 2007 test | mAP: 37.6 -> 41.7 | Improved |
| add self-paced data selection (ablation) | R-FCN ResNet50 · PASCAL VOC 2007 test | mAP: 27.2 -> 28.9 | Improved |
| add prior-knowledge filtration (ablation) | R-FCN ResNet50 · PASCAL VOC 2007 test | mAP: 28.6 -> 28.9 | Improved |
| add prior-knowledge filtration (ablation) | Fast R-CNN VGG16 · PASCAL VOC 2007 test | mAP: 32.8 -> 33.7 | Improved |
| add OHEM to R-FCN ResNet50 (ablation) | R-FCN ResNet50 · PASCAL VOC 2007 test | mAP: 28.9 -> 29.9 | Improved |
| add OHEM to ResNet101 detector in the three-model ensemble (ablation) | MSPLD · PASCAL VOC 2007 test | mAP: 41.7 -> 38.9 | Hurt |
| add OHEM to VGG16 detector in the three-model ensemble (ablation) | MSPLD · PASCAL VOC 2007 test | mAP: 41.7 -> 37.5 | Hurt |
| add EdgeBox proposals to Selective Search (ablation) | MSPLD · PASCAL VOC 2007 test | mAP: 41.7 -> 41.9 | No clear effect |
| replace Selective Search with EdgeBox proposals (ablation) | MSPLD · PASCAL VOC 2007 test | mAP: 41.7 -> 39.5 | Hurt |
Closest papers by meaning
- A Survey of Self-Supervised and Few-Shot Object Detection (TPAMI 2022 · similarity 0.92)
- Label, Verify, Correct: A Simple Few Shot Object Detection Method (CVPR 2022 · similarity 0.91)
- Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection (ECCV 2020 · similarity 0.91)
- Diverse Learner: Exploring Diverse Supervision for Semi-Supervised Object Detection (ECCV 2022 · similarity 0.89)
- Frustratingly Simple Few-Shot Object Detection (ICML 2020 · similarity 0.89)
- Meta-Learning to Detect Rare Objects (ICCV 2019 · similarity 0.89)
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.
