AI Paper Atlas

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

GTNet: Generative Transfer Network for Zero-Shot Object Detection

Shizhen Zhao, Changxin Gao, Yuanjie Shao, Lerenhan Li, Changqian Yu, Zhong Ji, Nong Sang

AAAI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 53 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
replace the visual-to-semantic mapping baseline with GTNet feature synthesis and unseen-class classificationGTNet · ILSVRC-2017mAP: 24.1 -> 26.0Improved
replace the visual-to-semantic mapping baseline with GTNet feature synthesis and unseen-class classificationGTNet · MSCOCO, IoU 0.5Recall@100: 34.3 -> 44.6Improved
replace the visual-to-semantic mapping baseline with GTNet feature synthesis and unseen-class classificationGTNet · Visual Genome, IoU 0.5Recall@100: 7.2 -> 11.3Improved
add CFU-generated unseen-class features (ablation)GTNet · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 18.1 -> 27.0; 3.0 -> 3.6; 16.3 -> 20.1Improved
add FFU to synthesize foreground features with IoU variance (ablation)GTNet with CFU · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 27.0 -> 39.2; 3.6 -> 7.5; 20.1 -> 24.5Improved
add BFU-generated class-specific background features (ablation)GTNet with CFU + FFU · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 39.2 -> 43.4; 7.5 -> 10.6; 24.5 -> 25.5Improved
add classification loss L_cls (ablation)IoUGAN · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 43.4 -> 44.3; 10.6 -> 10.9; 25.5 -> 25.7Improved
add embedding loss L_emb (ablation)IoUGAN · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 43.4 -> 44.9; 10.6 -> 10.8; 25.5 -> 25.8Improved
add both classification and embedding losses (ablation)IoUGAN · MSCOCO, Visual Genome, and ILSVRC-2017Recall@100 / mAP: 43.4 -> 44.6; 10.6 -> 11.3; 25.5 -> 26.0Mixed
use GTNet instead of the baseline detectorGTNet · MSCOCO GZSDperformance: 20.3 -> 42.5 (seen); 8.9 -> 30.4 (unseen)Improved

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