AI Paper Atlas

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

LMM-Det: Make Large Multimodal Models Excel in Object Detection

Jincheng Li, Chunyu Xie, Ji Ao, Dawei Leng, Yuhui Yin

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 4 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 COCO detection data to SFT (ablation)LLaVA-7B · COCO valAP: 0.2 -> 14.5Improved
add Object365 data at 336 resolution (ablation)LLaVA-7B · COCO valAP: 16.0 -> 15.6No clear effect
raise resolution 336 to 644 and add Object365 (ablation)LLaVA-7B · COCO valAP: 15.6 -> 38.7Improved
raise resolution 336 to 644 with COCO only (ablation)LLaVA-7B · COCO valAP: 16.0 -> 17.7Improved
replace CLIP-ViT with OWLv2-ViT (ablation)LMM-Det · COCO valAP: 38.7 -> 42.1Improved
add data distribution adjustment (ablation)LMM-Det with OWLv2-ViT · COCO valAP: 42.1 -> 44.2Improved
add inference optimization (per-category multi-step prediction) (ablation)LMM-Det · COCO valAP: 44.2 -> 47.5Improved
add inference optimization (ablation)LMM-Det · COCO valAR@100: 56.0 -> 63.6Improved
use OWLv2-ViT-L instead of DINOv2-L or CLIP-ViT-L (ablation)LMM-Det (COCO only) · COCO valAP: 16.0 -> 32.6Improved
add extra vocabularies for coordinate tokens (ablation)LMM-Det · COCO valAP: 32.6 -> 29.2Hurt
use beam search beam=2 instead of greedy decoding (ablation)LMM-Det · COCO valAP: 32.6 -> 33.0Mixed
use top-p sampling instead of greedy decoding (ablation)LMM-Det · COCO valAP: 32.6 -> 27.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 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