Research map / Detection and segmentation / Open-set and few-shot detection
Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection
Tianxue Ma, Mingwei Bi, Jian Zhang, Wang Yuan, Zhizhong Zhang, Yuan Xie, Shouhong Ding, Lizhuang Ma
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 MRSN mining/absorbing dual model (ablation) | Faster R-CNN baseline · PASCAL VOC Split 1 novel AP50 1-shot | AP50: 39.4 -> 43.6 | Improved |
| add MRSN (ablation) | Faster R-CNN baseline · PASCAL VOC Split 1 novel AP50 10-shot | AP50: 53.7 -> 59.7 | Improved |
| add PCC (ablation) | MRSN · PASCAL VOC Split 1 novel AP50 1-shot | AP50: 43.6 -> 44.9 | Improved |
| add PCC (ablation) | MRSN · PASCAL VOC Split 1 novel AP50 2-shot | AP50: 44.5 -> 47.7 | Improved |
| add UD-CutMix (ablation) | MRSN+PCC · PASCAL VOC Split 1 novel AP50 1-shot | AP50: 44.9 -> 47.6 | Improved |
| add UD-CutMix (ablation) | MRSN+PCC · PASCAL VOC Split 1 novel AP50 10-shot | AP50: 62.1 -> 62.6 | No clear effect |
| add SCCC contrastive loss instead of none (ablation) | MRSN+UD-CutMix · PASCAL VOC Split 1 novel AP50 3-shot | AP50: 55.0 -> 57.0 | Improved |
| use PCC instead of SCCC (ablation) | MRSN+UD-CutMix · PASCAL VOC Split 1 novel AP50 3-shot | AP50: 57.0 -> 57.8 | Improved |
| use PCC instead of SCCC (ablation) | MRSN+UD-CutMix · PASCAL VOC Split 1 novel AP50 10-shot | AP50: 60.9 -> 62.6 | Improved |
| raise mining-model update ratio from 0.001 to 0.5 (ablation) | MRSN · PASCAL VOC Split 1 3-shot novel AP50 | AP50: 57.8 -> 13.9 | Hurt |
| lengthen mining-model update interval from 1000 to 5000 iterations (ablation) | MRSN · PASCAL VOC Split 1 3-shot novel AP50 | AP50: 57.8 -> 52.9 | Hurt |
| shorten update interval from 1000 to 500 iterations (ablation) | MRSN · PASCAL VOC Split 1 3-shot novel AP50 | AP50: 57.8 -> 56.1 | Hurt |
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.
- FSCE — FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021) · better on 2 of 2 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
- Few-Shot Object Detection via Classification Refinement and Distractor Retreatment (CVPR 2021 · similarity 0.89)
- Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection (ECCV 2022 · similarity 0.88)
- FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021 · similarity 0.88)
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (CVPR 2020 · similarity 0.88)
- Few-Shot Object Detection with Foundation Models (CVPR 2024 · similarity 0.87)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.86)
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.
