AI Paper Atlas

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

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

Shuhuai Ren, Aston Zhang, Yi Zhu, Shuai Zhang, Shuai Zheng, Mu Li, Alex Smola, Xu Sun

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 12 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
remove local correction (adaptive margin) (ablation)POMP (K=1000) · 10 cross-dataset classification avgaccuracy (%): 65.8 -> 67.0Improved
remove local correction (adaptive margin) (ablation)POMP (K=1000) · ImageNet-21Kaccuracy (%): 25.0 -> 25.3Improved
increase sampled classes K from 100 to 1000 (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 65.5 -> 67.0Improved
use frequency-based negative sampling instead of uniform (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 67.0 -> 66.2Hurt
use similarity-based hard negative sampling instead of uniform (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 67.0 -> 64.2Hurt
margin m=1.5 instead of 1 at K=1000 (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 67.0 -> 66.4Hurt
margin m=1.5 instead of 1 at K=319 (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 66.2 -> 66.5Improved
prompt length 16 instead of 4 (ablation)POMP · 10 cross-dataset classification avgaccuracy (%): 67.0 -> 65.0Hurt
pre-train prompt on ImageNet-21K (POMP) instead of ImageNet-1K tuning (CoOp)CLIP ViT-B/16 · 10 cross-dataset classification avgaccuracy (%): 63.9 -> 67.0Improved
use local contrast sampling (K=128) instead of full class set when tuning on ImageNet-1KPOMP vs CoOp · ImageNet-1K 16-shotaccuracy (%): 71.9 -> 71.2No clear effect
use POMP prompt instead of hand-crafted prompts in ZSSegZSSeg · ADE20KmIoU: 20.2 -> 20.6Improved
POMP prompt instead of Detic promptDetic · LVIS AP_rAP_r: 26.7 -> 26.8No clear effect

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