AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

Jiaxi Wu, Songtao Liu, Di Huang, Yunhong Wang

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 401 citations (OpenAlex)

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 changedWhereMeasuredEffect
add MPSR refinement branchBaseline-FPN · VOC split 1, 1-shotmAP (%): 25.5 -> 41.7Improved
add MPSR refinement branchBaseline-FPN · VOC split 1, 10-shotmAP (%): 56.9 -> 61.8Improved
add MPSR refinement branchBaseline-FPN · COCO minival 30-shotAP (%): 13.7 -> 14.1Improved
add MPSR refinement branchBaseline-FPN · COCO minival 10-shotAP (%): 9.5 -> 9.8Improved
add MPSR refinement branchBaseline-FPN · COCO to VOC cross-dataset 10-shotmAP (%): 39.3 -> 42.3Improved
add FPN to Faster R-CNNBaseline · VOC split 1, 10-shotmAP (%): 47.9 -> 56.9Improved
add FPN to Faster R-CNNBaseline · VOC split 1, 1-shotmAP (%): 24.5 -> 25.5No clear effect
use manual feature-level selection instead of anchor matching on object pyramids (ablation)MPSR · VOC split 1, 1-shotmAP (%): 30.8 -> 41.7Improved
add RoI refinement to RPN-only refinement (ablation)MPSR · VOC split 1, 1-shotmAP (%): 36.7 -> 41.7Improved
add RPN refinement to RoI-only refinement (ablation)MPSR · VOC split 1, 1-shotmAP (%): 33.7 -> 41.7Improved
apply refinement in both base training and fine-tuning instead of only few-shot (ablation)MPSR · VOC split 1, 1-shotmAP (%): 36.5 -> 41.7Improved
apply refinement in both steps instead of only base training (ablation)MPSR · VOC split 1, 1-shotmAP (%): 26.6 -> 41.7Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy