# ECO: Ensembling Context Optimization for Vision-Language Models

Source: [ECO: Ensembling Context Optimization for Vision-Language Models](<https://www.sota2.com/research/paper/68fa70281e209131cea49780>)

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

Data updated: 2025-10-26T01:35:15.802Z

Authors: Lorenzo Agnolucci, Alberto Baldrati, Francesco Todino, Federico Becattini, Marco Bertini, Alberto Del Bimbo

Published: 2023-07-26T09:31:06.000Z

## Abstract

Image recognition has recently witnessed a paradigm shift, where vision-language models are now used to perform few-shot classification based on textual prompts. Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space. This has paved the way for several works that focus on engineering or learning textual contexts for maximizing CLIP's classification capabilities. In this paper, we follow this trend by learning an ensemble of prompts for image classification. We show that learning diverse and possibly shorter contexts improves considerably and consistently the results rather than relying on a single trainable prompt. In particular, we report better few-shot capabilities with no additional cost at inference time. We demonstrate the capabilities of our approach on 11 different benchmarks.

## 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/2307.14063>)

[PDF](<https://arxiv.org/pdf/2307.14063.pdf>)