AI Paper Atlas

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

X-DETR: A Versatile Architecture for Instance-Wise Vision-Language Tasks

Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 48 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
split merged paragraph queries into independent queries (mixed*) (ablation)X-DETR (ResNet-50) · LVIS, no finetuningAP: 11.5 -> 13.5Improved
split merged paragraph queries into independent queries (mixed*) (ablation)X-DETR (ResNet-50) · RefCOCO MMIS-style ablation R@1, no finetuningR@1: 63.9 -> 75.4Improved
add COCO boxes without category (mixed*+boxes) (ablation)X-DETR (ResNet-50) · LVIS, no finetuningAP: 13.5 -> 14.7Improved
add COCO boxes without category (mixed*+boxes) (ablation)X-DETR (ResNet-50) · RefCOCO, no finetuningR@1: 75.4 -> 78.0Improved
add CC image-caption data (ablation)X-DETR (ResNet-50) · LVIS, no finetuningAP: 14.7 -> 15.9Improved
add CC image-caption data (ablation)X-DETR (ResNet-50) · RefCOCO, no finetuningR@1: 78.0 -> 76.9Hurt
add LocNar pseudo-labeled data and OpenImages boxes (ablation)X-DETR (ResNet-50) · Flickr30k phrase grounding, no finetuningR@1: 80.1 -> 81.3Improved
add LocNar pseudo-labeled data and OpenImages boxes (ablation)X-DETR (ResNet-50) · MMIS on RefCOCOg, no finetuningR@5: 22.2 -> 21.0Hurt
add LocNar pseudo-labeled data and OpenImages boxes (ablation)X-DETR (ResNet-50) · LVIS, finetuned on 10%AP: 23.3 -> 25.6Improved
replace joint-modality transformer alignment (MDETR) with dot-product alignmentX-DETR · LVIS 10% finetuningAP: 24.2 -> 29.5Improved
replace joint-modality transformer alignment (MDETR) with dot-product alignmentX-DETR · RefCOCO val MMIS, no finetuningR@10: 2.5 -> 30.8Improved
add context region (expanded box) to R-CLIP (ablation)R-CLIP · LVIS OVOD, 0% finetuningAP: 12.7 -> 13.7Improved

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