AI Paper Atlas

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

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Lewei Yao, Jianhua Han, Youpeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Chunjing Xu, Hang Xu

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 64 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 sequential formulation with paralleled concept formulation (ablation)detector trained on O365 · LVIS minival zero-shotAP: 23.7 -> 27.8Improved
add concept enrichment with definitions (ablation)paralleled detector, O365 · LVIS minival zero-shotAP: 27.8 -> 28.8Improved
add concept enrichment with definitions (ablation)paralleled detector, O365+GoldG · LVIS minival zero-shotAP: 28.2 -> 32.2Improved
add negative categories sampled from concept dictionary (ablation)paralleled detector with enrichment, O365+GoldG · LVIS minival zero-shotAP: 32.2 -> 34.4Improved
add YFCC image-text pseudo-labeled data (ablation)DetCLIP-T · LVIS minival zero-shotAP: 34.4 -> 35.5Improved
add label completion with concept dictionary in pseudo labeling (ablation)DetCLIP-T · LVIS minival zero-shotAP: 35.5 -> 35.9Improved
add label completion with concept dictionary (ablation)DetCLIP-T · 13 downstream datasetsAP: 39.9 -> 43.3Improved
add GoldG grounding data without enrichment to paralleled model (ablation)paralleled detector · LVIS minival zero-shotAP: 27.8 -> 28.2Mixed
use small concept dictionary (O365, 0.36K) vs no dictionary (ablation)DetCLIP-T(B) · LVIS minival zero-shotAP: 28.2 -> 27.8Hurt
scale dictionary to ~14K concepts vs no dictionary (ablation)DetCLIP-T(B) · LVIS minival zero-shotAP: 28.2 -> 34.4Improved
include class definitions at inference (ablation)DetCLIP-T(B) · LVIS minival zero-shotAP: 30.4 -> 34.4Improved
shuffle word order in grounding data (ablation)sequential formulation · LVIS minival zero-shotAP: 26.0 -> 27.4Improved

Later papers that compared with this method

8 later accepted papers report DetCLIPv2 as a baseline in their results tables; 6 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