IC3: Image Captioning by Committee Consensus

David Chan, Austin Myers, Sudheendra Vijayanarasimhan, David A Ross, John Canny

Submission Type: Regular Long Paper

Submission Track: Language Grounding to Vision, Robotics and Beyond

Submission Track 2: Theme Track: Large Language Models and the Future of NLP

Keywords: Image Captioning, Large Language Models, Prompt Engineering, Visual Description

TL;DR: IC3 is a visual description method which generates a set of candidate captions, then summarizes them to generate high quality image descriptions.

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/](https://davidmchan.github.io/caption-by-committee/)

Submission Number: 596