Saved in:
Bibliographic Details
Main Authors: Kamboj, Payal, Banerjee, Ayan, Xu, Bin, Gupta, Sandeep
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.16481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917904083058688
author Kamboj, Payal
Banerjee, Ayan
Xu, Bin
Gupta, Sandeep
author_facet Kamboj, Payal
Banerjee, Ayan
Xu, Bin
Gupta, Sandeep
contents Rare events, due to their infrequent occurrences, do not have much data, and hence deep learning techniques fail in estimating the distribution for such data. Open-vocabulary models represent an innovative approach to image classification. Unlike traditional models, these models classify images into any set of categories specified with natural language prompts during inference. These prompts usually comprise manually crafted templates (e.g., 'a photo of a {}') that are filled in with the names of each category. This paper introduces a simple yet effective method for generating highly accurate and contextually descriptive prompts containing discriminative characteristics. Rare event detection, especially in medicine, is more challenging due to low inter-class and high intra-class variability. To address these, we propose a novel approach that uses domain-specific expert knowledge on rare events to generate customized and contextually relevant prompts, which are then used by large language models for image classification. Our zero-shot, privacy-preserving method enhances rare event classification without additional training, outperforming state-of-the-art techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16481
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating customized prompts for Zero-Shot Rare Event Medical Image Classification using LLM
Kamboj, Payal
Banerjee, Ayan
Xu, Bin
Gupta, Sandeep
Computer Vision and Pattern Recognition
Rare events, due to their infrequent occurrences, do not have much data, and hence deep learning techniques fail in estimating the distribution for such data. Open-vocabulary models represent an innovative approach to image classification. Unlike traditional models, these models classify images into any set of categories specified with natural language prompts during inference. These prompts usually comprise manually crafted templates (e.g., 'a photo of a {}') that are filled in with the names of each category. This paper introduces a simple yet effective method for generating highly accurate and contextually descriptive prompts containing discriminative characteristics. Rare event detection, especially in medicine, is more challenging due to low inter-class and high intra-class variability. To address these, we propose a novel approach that uses domain-specific expert knowledge on rare events to generate customized and contextually relevant prompts, which are then used by large language models for image classification. Our zero-shot, privacy-preserving method enhances rare event classification without additional training, outperforming state-of-the-art techniques.
title Generating customized prompts for Zero-Shot Rare Event Medical Image Classification using LLM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.16481