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

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

10 Apr 2023NeurIPS 2023 11arXiv:2304.04704archive 2025-07-28

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

This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over twenty-thousand classes. Once pre-trained, the prompt with a strong transferable ability can be directly plugged into a variety of visual recognition tasks including image classification, semantic segmentation, and object detection, to boost recognition performances in a zero-shot manner. Empirical evaluation shows that POMP achieves state-of-the-art performances on 21 datasets, e.g., 67.0% average accuracy on 10 classification datasets (+3.1% compared to CoOp) and 84.4 hIoU on open-vocabulary Pascal VOC segmentation (+6.9 compared to ZSSeg). Our code is available at https://github.com/amazon-science/prompt-pretraining.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.04704")

Code

Syntology Ran 5 of 7 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

amazon-science/prompt-pretraining officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
2ran
2unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from amazon-science/prompt-pretraining. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

align_loss amazon-science/prompt-pretraining/align_uniform.py official repository ran fingerprinted Apache-2.0 (permissive) · ebb1a59bc40babbb · report
basic_clean amazon-science/prompt-pretraining/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 98f385d847636a3e · report
get_pairs amazon-science/prompt-pretraining/clip/simple_tokenizer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d919ae32e5e4e616 · report
uniform_loss amazon-science/prompt-pretraining/align_uniform.py official repository ran fingerprinted Apache-2.0 (permissive) · 8d3d5f756818e024 · report
whitespace_clean amazon-science/prompt-pretraining/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9542161e9640b858 · report
build_model amazon-science/prompt-pretraining/clip/model.py official repository unverified Apache-2.0 (permissive) · 81ce35f8e245e82e · report
load amazon-science/prompt-pretraining/clip/clip.py official repository unverified Apache-2.0 (permissive) · 3776e3e7d4b86f52 · report

Tasks

Image ClassificationObject DetectionSegmentationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Object Detection LVIS v1.0 POMP AP novel-LVIS base training 25.2 #16 of 28 Archive leaderboard report
Open Vocabulary Semantic Segmentation COCO-Stuff-171 POMP HIoU 39.1 #1 of 7 Archive leaderboard report
Open Vocabulary Semantic Segmentation PascalVOC-20 POMP hIoU 84.4 #13 of 20 Archive leaderboard report
Open Vocabulary Semantic Segmentation PascalVOC-20 POMP mIoU 89.4 #13 of 20 Archive leaderboard report
Prompt Engineering ImageNet-21k POMP Accuracy 25.3 #1 of 2 Archive leaderboard report
Prompt Engineering ImageNet-A POMP Top-1 accuracy % 51.6 #1 of 9 Archive leaderboard report
Prompt Engineering ImageNet-R POMP Top-1 accuracy % 77.9 #1 of 9 Archive leaderboard report
Prompt Engineering ImageNet-S POMP Top-1 accuracy % 49.8 #1 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections