AI Paper Atlas

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

LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction

Penghui Du, Yu Wang, Yifan Sun, Luting Wang, Yue Liao, gang zhang, Errui Ding, Yan Wang, Jingdong Wang, Si Liu

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 15 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 language embedding fusion to the detector queries (ablation)LaMI-DETR · OV-LVISAP_r: 32.2 -> 33.0Improved
add visual concept sampling (cluster visual descriptions, sample easy negatives) (ablation)LaMI-DETR · OV-LVISAP_r: 33.0 -> 40.1Improved
add embedding update with visual descriptions (ablation)LaMI-DETR · OV-LVISAP_r: 40.1 -> 42.5Improved
add confusing-category prompts at inference (ablation)LaMI-DETR · OV-LVISAP_r: 42.5 -> 43.4Improved
regenerate descriptions to emphasize differences from the most confusable category (ablation)CLIP text classifier · LVIS minival proposal classificationmAcc_r: 49.5 -> 52.7Improved
cluster with CLIP text name embeddings for visual concept sampling (ablation)baseline+VCS · OV-LVISAP_r: 33.0 -> 33.5No clear effect
cluster T5 name embeddings instead of CLIP (ablation)baseline+VCS · OV-LVISAP_r: 33.5 -> 34.1No clear effect
cluster name plus definition embeddings (DetCLIP-style enrichment) (ablation)baseline+VCS · OV-LVISAP_r: 33.0 -> 31.5Hurt
cluster name plus visual description embeddings (ablation)baseline+VCS · OV-LVISAP_r: 34.1 -> 40.1Improved
multiply novel-class logits by factor 5.0 at inference (ablation)baseline+LaMI · OV-LVISAP_r: 41.7 -> 43.4 AP_r; AP 41.1 -> 41.3Mixed
LaMI-DETR vs strongest prior OV-LVIS methodLaMI-DETR · OV-LVISAP_r: 35.6 -> 43.4Improved

Later papers that compared with this method

1 later accepted paper reports LaMI-DETR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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