IC3: Image Captioning by Committee Consensus

TL;DR

IC3 introduces a novel ensemble approach for image captioning that synthesizes multiple viewpoints to produce more comprehensive and informative captions, outperforming existing state-of-the-art models in human and automated evaluations.

Contribution

The paper proposes a new committee consensus method for image captioning that captures diverse scene details, improving caption informativeness and system recall performance.

Findings

IC3 captions are rated as helpful as top models by humans over two-thirds of the time.

IC3 enhances automated recall system performance by up to 84%.

IC3 outperforms single-reference captions and state-of-the-art approaches.

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/