Research map / Detection and segmentation / Open-set and few-shot detection
PromptDet: Towards Open-Vocabulary Detection Using Uncurated Images
Chengjian Feng, Yujie Zhong, Zequn Jie, Xiangxiang Chu, Haibing Ren, Xiaolin Wei, Weidi Xie, Lin Ma
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add description to manual prompt (ablation) | PromptDet detector · LVIS minival | AP_novel: 7.4 -> 9.0 | Improved |
| use regional prompt learning instead of manual description prompt (ablation) | PromptDet detector · LVIS minival | AP_novel: 9.0 -> 11.1 | Improved |
| add self-training to manual description prompt (ablation) | PromptDet · LVIS minival | AP_novel: 9.0 -> 15.3 | Improved |
| add self-training to learned prompt (1-iter) (ablation) | PromptDet · LVIS minival | AP_novel: 11.1 -> 15.9 | Improved |
| add second iteration of prompt learning and image sourcing (ablation) | PromptDet · LVIS minival | AP_novel: 15.9 -> 19.0 | Improved |
| add third iteration of prompt learning (ablation) | PromptDet · LVIS minival | AP_novel: 19.0 -> 19.3 | No clear effect |
| use max-prediction-score boxes instead of max-size (ablation) | PromptDet · LVIS minival | AP_novel: 9.5 -> 19.0 | Improved |
| increase sourced web images from 50 to 300 (ablation) | PromptDet · LVIS minival | AP_novel: 14.6 -> 19.0 | Improved |
| update RPN classifier and box head during self-training (ablation) | PromptDet · LVIS minival | AP_novel: 17.2 -> 19.0 | Improved |
| use top-20 proposals instead of all proposals for pseudo labels (ablation) | PromptDet · LVIS minival | AP_novel: 10.4 -> 19.0 | Improved |
| use top-20 instead of top-30 proposals (ablation) | PromptDet · LVIS minival | AP_novel: 16.1 -> 19.0 | Improved |
| train longer (12 to 72 epochs) | PromptDet · LVIS minival | AP_c: 18.5 -> 23.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DLWL — DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data (CVPR 2020) · better on 2 of 2 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
- DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection (NeurIPS 2025 · similarity 0.89)
- Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm (AAAI 2025 · similarity 0.89)
- LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors (ICLR 2024 · similarity 0.89)
- Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection (CVPR 2024 · similarity 0.88)
- DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection (NeurIPS 2024 · similarity 0.88)
- LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models (CVPR 2025 · similarity 0.88)
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.
