AI Paper Atlas

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

Universal-Prototype Enhancing for Few-Shot Object Detection

Aming Wu, Yahong Han, Linchao Zhu, Yi Yang

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 131 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 conditional (affine-transformed) prototypes instead of raw universal prototypes (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 43.8 -> 47.8Improved
add conditional (affine-transformed) prototypes instead of raw universal prototypes (ablation)FSOD-up · PASCAL VOC Novel Set 1, 1-shotnovel mAP (%): 38.1 -> 43.8Improved
use conditional prototypes instead of a new set of prototypes (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 44.6 -> 47.8Improved
use conditional prototypes instead of a new set of prototypes (ablation)FSOD-up · PASCAL VOC Novel Set 1, 5-shotnovel mAP (%): 56.1 -> 55.4Hurt
use 24 universal prototypes instead of 16 (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 42.7 -> 47.8Improved
use 24 universal prototypes instead of 32 (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 42.1 -> 47.8Improved
set consistency loss weight gamma to 1.0 instead of 0.8 (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 42.5 -> 47.8Improved
set consistency loss weight gamma to 1.0 instead of 1.4 (ablation)FSOD-up · PASCAL VOC Novel Set 1, 2-shotnovel mAP (%): 43.5 -> 47.8Improved
fuse prototype descriptors into RPN input (ablation)FSOD-up · PASCAL VOC Novel Set 1, 1-shot and 5-shotnovel mAP (%): +2.7% (1-shot), +1.8% (5-shot)Improved
fuse prototype descriptors into classifier input (ablation)FSOD-up · PASCAL VOC Novel Set 1, 1-shot and 5-shotnovel mAP (%): +2.1% (1-shot), +1.2% (5-shot)Improved
use FSOD-up instead of MPSRFSOD-up · PASCAL VOC Novel Set 2, 1-shotnovel mAP (%): 24.4 -> 31.2Improved
use FSOD-up instead of MPSRFSOD-up · PASCAL VOC Novel Set 1, 5-shot vs TFA w/cosnovel mAP (%): 55.7 -> 55.4No clear effect

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