AI Paper Atlas

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

Contextual Object Detection with Multimodal Large Language Models

Yuhang Zang, Wei Li, Jun Han, Kaiyang Zhou, Chen Change Loy

IJCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 180 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 local visual tokens as LLM prefix (ablation)ContextDET · CODE val cloze testAcc@1: 30.9 -> 48.7Improved
add local visual tokens as LLM prefix (ablation)ContextDET · CODE val cloze testAP@1: 4.0 -> 10.4Improved
use p=9 local tokens instead of 4 (ablation)ContextDET · CODE val cloze testAP@1: 10.1 -> 10.4Improved
use p=9 local tokens instead of 16 (ablation)ContextDET · CODE val cloze testAP@1: 9.9 -> 10.4Improved
replace ResNet50 with Swin-B backbone (ablation)ContextDET (OPT-2.7B) · CODE val cloze testAP@1: 10.2 -> 13.1Improved
replace OPT-2.7B with OPT-6.7B (Swin-B) (ablation)ContextDET · CODE val cloze testAP@1: 13.1 -> 13.7Improved
replace OPT-2.7B with OPT-6.7B (ResNet50) (ablation)ContextDET · CODE val cloze testAP@1: 10.2 -> 11.1Improved
end-to-end ContextDET instead of cascade LLaVA1.5+GLIPContextDET · CODE val cloze testAcc@1: 42.9 -> 48.7Improved
fine-tune GLIP on CODE in cascadeLLaVA1.5+GLIP · CODE val cloze testAP@1: 9.2 -> 9.1No clear effect
use ContextDET instead of BARON on OV-COCOContextDET · OV-COCO (novel classes)AP50 novel: 34.0 -> 36.8Improved
use ContextDET instead of PolyFormerContextDET · RefCOCO valmIoU: 75.96 -> 76.40Improved
use ContextDET instead of Deformable DETRContextDET · COCO valAP: 46.2 -> 43.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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