# Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions

Source: [Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions](<https://www.sota2.com/research/paper/68fa6cf11e209131cea36b57>)

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

Data updated: 2025-10-26T00:21:36.840Z

Authors: Kosuke Nishida, Kyosuke Nishida, Shuichi Nishioka

Published: 2022-07-07T07:48:06.000Z

## Abstract

Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our proposed model, LIDE (Learning from Image and DEscription), has a text decoder to generate the descriptions and a text encoder to obtain the text representations of machine- or user-generated descriptions. We confirmed that LIDE with machine-generated descriptions outperformed baseline models. Moreover, the performance was improved further with high-quality user-generated descriptions. The generated descriptions can be viewed as the explanations of the model's predictions, and we observed that such explanations were consistent with prediction results. We also investigated why the language description improved the few-shot image classification performance by comparing the image representations and the text representations in the feature spaces.

## 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/2207.03133>)

[PDF](<https://arxiv.org/pdf/2207.03133.pdf>)