AI Paper Atlas

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

Improved Visual-Semantic Alignment for Zero-Shot Object Detection

Shafin Rahman, Salman Khan, Nick Barnes

AAAI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 109 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 focal loss with polarity loss (ablation)Our-FL-word · MS-COCO 65/15 ZSDmAP: 10.80 -> 12.02Improved
replace focal loss with polarity loss (ablation)Our-FL-word · MS-COCO 65/15 GZSD seenmAP: 37.56 -> 33.28Hurt
add vocabulary metric learning (ablation)Our-PL-word · MS-COCO 65/15 ZSDmAP: 12.02 -> 12.62Improved
use word vectors during training (ablation)Baseline RetinaNet · MS-COCO 65/15 ZSDmAP: 8.48 -> 10.80Improved
use word vectors during training (ablation)Baseline RetinaNet · MS-COCO 65/15 GZSD seenmAP: 36.96 -> 37.56Hurt
add word vectors in box-regression subnet (ablation)Ours · MS-COCO 65/15 ZSDmAPImproved
full method vs baselineRetinaNet · MS-COCO 65/15 GZSDharmonic mAP: 14.03 -> 18.18Improved
use small top-T seen semantics (T=5) instead of all (ablation)Ours · MS-COCOmAPImproved
use polarity loss with balanced CE only (gamma=0) (ablation)Ours · MS-COCO ZSDmAP: around 10% mAPNo 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