IC3: Image Captioning by Committee Consensus
Chan, David M., Myers, Austin, Vijayanarasimhan, Sudheendra, Ross, David A., Canny, John
–arXiv.org Artificial Intelligence
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/
arXiv.org Artificial Intelligence
Oct-19-2023
- Country:
- Oceania > Australia
- North America > United States
- Maryland > Baltimore (0.04)
- Texas (0.04)
- District of Columbia > Washington (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Colorado > Denver County
- Denver (0.04)
- Ohio > Franklin County
- Columbus (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Washington > King County
- Seattle (0.04)
- California
- Los Angeles County > Long Beach (0.04)
- Alameda County > Berkeley (0.04)
- New York > New York County
- New York City (0.04)
- Europe
- Austria > Vienna (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy > Veneto
- Venice (0.04)
- Germany > North Rhine-Westphalia
- Cologne Region > Bonn (0.04)
- France > Grand Est
- Bas-Rhin > Strasbourg (0.04)
- Estonia > Harju County
- Tallinn (0.04)
- Asia
- South Korea > Seoul
- Seoul (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- China > Heilongjiang Province
- Daqing (0.04)
- South Korea > Seoul
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Leisure & Entertainment > Sports > Tennis (0.68)
- Technology: