SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.04704 · 2023

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
amazon-science/prompt-pretraining canonical 5 of 7
FunctionStatusWhere it lives
align_loss Ran amazon-science/prompt-pretraining/align_uniform.py
code served (permissive licence) · get_code("ebb1a59bc40babbb")
basic_clean Ran amazon-science/prompt-pretraining/clip/simple_tokenizer.py
code served (permissive licence) · get_code("98f385d847636a3e")
get_pairs Ran amazon-science/prompt-pretraining/clip/simple_tokenizer.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
uniform_loss Ran amazon-science/prompt-pretraining/align_uniform.py
code served (permissive licence) · get_code("8d3d5f756818e024")
whitespace_clean Ran amazon-science/prompt-pretraining/clip/simple_tokenizer.py
code served (permissive licence) · get_code("9542161e9640b858")
build_model Not yet run amazon-science/prompt-pretraining/clip/model.py
code served (permissive licence) · get_code("81ce35f8e245e82e")
load Not yet run amazon-science/prompt-pretraining/clip/clip.py
code served (permissive licence) · get_code("3776e3e7d4b86f52")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.04704")
get_code_for_paper("2304.04704")
have("2304.04704")

Connect an agent — have() is free.