AI Paper Atlas

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

Few-Shot Object Detection via Feature Reweighting

Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 917 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
apply reweighting at layer 21 instead of layer 13 (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 40.7 -> 47.2Improved
apply reweighting at layer 21 instead of layer 20 (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 43.6 -> 47.2Improved
reweight all layer 21 features instead of half (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 46.9 -> 47.2No clear effect
use softmax loss instead of single-binary loss (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 14.8 -> 47.2Improved
use softmax loss instead of multi-binary loss (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 41.6 -> 47.2Improved
add the mask channel to image input of reweighting module (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 43.3 -> 47.2Improved
add cropped object input on top of image+mask (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 47.2 -> 46.8No clear effect
average reweighting vectors of k-shot examples at test time instead of random single example (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 45.1 -> 47.2Improved
do not share weights between feature extractor and reweighting module (ablation)feature reweighting detector · PASCAL VOC novel set 1, 10-shotnovel mAP: 44.8 -> 47.2Improved
two-phase training (base training then few-shot fine-tuning) instead of joint trainingYOLOv2 baseline · PASCAL VOC novel set 1, 10-shotnovel mAP: 1.8 -> 38.6Improved
add feature reweighting module to YOLOv2 few-shot fine-tuningYOLOv2 · PASCAL VOC novel set 1, 1-shotnovel mAP: 6.6 -> 14.8Improved
add LSTD background depression and transfer knowledge to YOLO-ft-fullYOLO-ft-full · PASCAL VOC novel set 2, 5-shotnovel mAP: -5.1 mAPHurt

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