Research map / Detection and segmentation / CNN features
Kernelized Few-Shot Object Detection With Efficient Integral Aggregation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 KFSOD instead of FSODup | few-shot object detection · PASCAL VOC 2007 test, 1-shot, mean over splits | mAP: 36.8±5.2 -> 39.1±3.8 | Helped |
| use KFSOD instead of FSODup | few-shot object detection · PASCAL VOC 2007 test, 3-shot, mean over splits | mAP: 45.1±3.8 -> 47.2±5.1 | Helped |
| use KFSOD instead of FSCE | few-shot object detection · PASCAL VOC 2007 test, 5-shot, mean over splits | mAP: 51.1±7.7 -> 53.9±3.6 | Helped |
| use KFSOD instead of FSCE | few-shot object detection · PASCAL VOC 2007 test, 10-shot, mean over splits | mAP: 55.9±5.6 -> 56.7±6.0 | Helped |
| use KFSOD instead of FSODup | few-shot object detection · MS COCO minival, 20 novel classes, 10-shot | AP: 11.6 -> 18.5 | Helped |
| use KFSOD instead of FSODup | few-shot object detection · MS COCO minival, 20 novel classes, 10-shot | AP50: 23.9 -> 26.3 | Helped |
| use KFSOD instead of FSODup | few-shot object detection · MS COCO minival, 20 novel classes, 10-shot | AP75: 9.8 -> 18.7 | Helped |
| use KFSOD instead of PNSD | few-shot object detection · FSOD test, 5-shot | AP50: 29.8 -> 33.4 | Helped |
| use KFSOD instead of PNSD | few-shot object detection · FSOD test, 5-shot | AP75: 22.6 -> 29.6 | Helped |
| combine linear, RBF and polynomial kernels (ablation) | KFSOD · FSOD test, 5-shot | AP50: 30.6 -> 32.2 | Helped |
| combine linear, RBF and polynomial kernels (ablation) | KFSOD · COCO, 10-shot | AP75: 12.4 -> 14.6 | Helped |
| add count sketching to IRA and kernel aggregation (ablation) | KFSOD · PASCAL VOC 2007, 5-shot, novel classes, split 1 | mAP: ∼1.8% | Helped |
Closest papers by meaning
- Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss (CVPR 2021 · similarity 0.89)
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (CVPR 2020 · similarity 0.87)
- Few-Shot Object Detection via Variational Feature Aggregation (AAAI 2023 · similarity 0.87)
- Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment (AAAI 2022 · similarity 0.87)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.86)
- Multi-Perspective Data Augmentation for Few-shot Object Detection (ICLR 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.