SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.15243 · ICML · 2023

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

Zongbo Han, Changqing Zhang, Qinghua Hu, Yichen Bai, Bing Cao, Xiaoheng Jiang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 3 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
ycfate/id-like canonical 3 of 7
FunctionStatusWhere it lives
basic_clean Ran ycfate/id-like/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("98f385d847636a3e")
get_pairs Ran ycfate/id-like/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
whitespace_clean Ran ycfate/id-like/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("9542161e9640b858")
build_model Not yet run ycfate/id-like/clip/model.py
pointer only (licence: NONE) · get_code("aa56b568a90f8516")
get_loss Not yet run ycfate/id-like/utils/id_like_loss.py
pointer only (licence: NONE) · get_code("39f12edcbfe6882e")
load Not yet run ycfate/id-like/clip/clip.py
pointer only (licence: NONE) · get_code("88d0e8acec4aead0")
select_in_out Not yet run ycfate/id-like/utils/id_like.py
pointer only (licence: NONE) · get_code("6a21d81fd81655e0")

Repositories linked to this paper

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

Abstract

Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However, they may still face limitations in effectively distinguishing between the most challenging OOD samples that are much like in-distribution (ID) data, i.e., ID-like samples. To this end, we propose a novel OOD detection framework that discovers ID-like outliers using CLIP [28] from the vicinity space of the ID samples, thus helping to identify these most challenging OOD samples. Then a prompt learning framework is proposed that utilizes the identified ID-like outliers to further leverage the capabilities of CLIP for OOD detection. Benefiting from the powerful CLIP, we only need a small number of ID samples to learn the prompts of the model without exposing other auxiliary outlier datasets. By focusing on the most challenging ID-like OOD samples and elegantly exploiting the capabilities of CLIP, our method achieves superior few-shot learning performance on various real-world image datasets (e.g., in 4-shot OOD detection on the ImageNet-1k dataset, our method reduces the average FPR95 by 12.16% and improves the average AUROC by 2.76%, compared to state-of-the-art methods).

For agents

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

get_harvested_code_for_paper("2311.15243")
get_code_for_paper("2311.15243")
have("2311.15243")

Connect an agent — have() is free.