# IC3: Image Captioning by Committee Consensus

Source: [IC3: Image Captioning by Committee Consensus](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dce6>)

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

Data updated: 2025-10-26T01:52:52.049Z

Authors: David M. Chan, Austin Myers, Sudheendra Vijayanarasimhan, David A. Ross, John Canny

Published: 2023-02-02T18:58:05.000Z

## Abstract

If you ask a human to describe an image, they might do so in a thousand different ways. Traditionally, image captioning models are trained to generate a single "best" (most like a reference) image caption. Unfortunately, doing so encourages captions that are "informationally impoverished," and focus on only a subset of the possible details, while ignoring other potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: "Image Captioning by Committee Consensus" (IC3), designed to generate a single caption that captures high-level details from several annotator viewpoints. Humans rate captions produced by IC3 at least as helpful as baseline SOTA models more than two thirds of the time, and IC3 can improve the performance of SOTA automated recall systems by up to 84%, outperforming single human-generated reference captions, and indicating significant improvements over SOTA approaches for visual description. Code is available at https://davidmchan.github.io/caption-by-committee/

## 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.

- [Pseudo-captioning on HM3D (test)](<https://www.sota2.com/research/sota/pseudo-captioning-on-hm3d-test.md>): Pseudo-captioning; HM3D (test); B4 Score: 1.36.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2302.01328>)

[PDF](<https://arxiv.org/pdf/2302.01328.pdf>)
