AI Paper Atlas

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

Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark

Kibok Lee, Hao Yang, Satyaki Chakraborty, Zhaowei Cai, Gurumurthy Swaminathan, Avinash Ravichandran, Onkar Dabeer

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection

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
tune whole network instead of detection head only (FSCE-base) (ablation)Faster R-CNN · MoFSOD 1-shotAP50: outperforms FSCE-base by 1.0%Improved
tune whole network instead of last FC layers only (TFA) (ablation)Faster R-CNN · MoFSOD 1-shotAP50: 8.1%Improved
tune whole network instead of detection head / last FC layers (ablation)Faster R-CNN · MoFSOD 10-shotAP50: 2.4%, 17.4%Improved
tune last FC layers only on datasets close to COCO (KITTI, iWildCam) (ablation)TFA · MoFSOD 5-shot per datasetAP50: 71.7 vs 63.3 iWildCam; 48.3 vs 45.3 KITTIMixed
replace Faster R-CNN with RetinaNet (ablation)FT · MoFSODAP50: 4--6% low performanceHurt
Cascade R-CNN instead of Faster R-CNN (ablation)FT · MoFSODAP50: 31.5 -> 31.5 (1-shot)No clear effect
add FPN-P67 to Cascade R-CNN (ablation)FT · MoFSODAP50: 3--4%Improved
CenterNet2 instead of Faster R-CNN (ablation)FT · MoFSOD 1-shotAP50: lower, e.g. 2.4% in 1-shotHurt
Deformable-DETR instead of Faster R-CNN (ablation)FT · MoFSOD 10-shotAP50: 2.1% on MoFSOD in 10-shotImproved
pre-train on ImageNet instead of COCO (ablation)Cascade R-CNN-P67 · MoFSOD 5-shotAP50: 49.9 -> 29.5Hurt
pre-train on Unified or LVIS instead of COCO (ablation)Cascade R-CNN-P67 · MoFSOD 5-shotAP50: 49.9 -> 49.6No clear effect
initialize classifier with CLIP text embeddings (LVIS+) (ablation)CenterNet2 · MoFSOD 5-shotAP50: 7.5%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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