# Exploiting LMM-based knowledge for image classification tasks

Source: [Exploiting LMM-based knowledge for image classification tasks](<https://www.sota2.com/research/paper/68fa73721e209131cea5c900>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:50:15.439Z

Authors: Maria Tzelepi, Vasileios Mezaris

Published: 2024-06-05T08:56:24.000Z

## Abstract

In this paper we address image classification tasks leveraging knowledge encoded in Large Multimodal Models (LMMs). More specifically, we use the MiniGPT-4 model to extract semantic descriptions for the images, in a multimodal prompting fashion. In the current literature, vision language models such as CLIP, among other approaches, are utilized as feature extractors, using only the image encoder, for solving image classification tasks. In this paper, we propose to additionally use the text encoder to obtain the text embeddings corresponding to the MiniGPT-4-generated semantic descriptions. Thus, we use both the image and text embeddings for solving the image classification task. The experimental evaluation on three datasets validates the improved classification performance achieved by exploiting LMM-based knowledge.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.03071>)

[PDF](<https://arxiv.org/pdf/2406.03071.pdf>)