ΑΙhub.org
 

New algorithm follows human intuition to make visual captioning more grounded

visual captions | AIhub

Annotating and labeling datasets for machine learning problems is an expensive and time-consuming process for computer vision and natural language scientists. However, a new deep learning approach is being used to decode, localize, and reconstruct image and video captions in seconds, making the machine-generated captions more reliable and trustworthy.

To solve this problem, researchers at the Machine Learning Center at Georgia Tech (ML@GT) and Facebook have created the first cyclical algorithm that can be applied to visual captioning models. The model is able to use the three-step processing during training to make the model more visually-grounded without human annotations or introducing additional computations when deployed, saving researchers time and money on their datasets.

The algorithm employs attention mechanisms, an intuitive concept for humans, when looking at a photo or video. This means that it tries to determine what aspects are important in an image and sequentially create a sentence explaining the visual.

This new model helps solve issues with previous attempts where an algorithm would make its decision based on prior linguistic biases instead of what it is actually “seeing.” This would lead to algorithms having what researchers refer to as object hallucinations. Object hallucinations occur when an algorithmic model assumes an object like a table is in a photo because in previous images, someone with a laptop was always sitting at a table. In this instance, the model is unable to understand a situation where a person has a laptop on their lap instead of a table. This new model helps alleviate the object hallucination problem, thus making the model more reliable and trustworthy.

Chih-Yao MaChih-Yao Ma, a Ph.D. student in the School of Electrical and Computer Engineering, envisions this model being used in situations like describing what happens in the scene as a technology to assist people who are visually impaired to overcome their real daily visual challenges. The model would be a good fit in such instances, because it can alleviate the linguistic bias and object hallucination issues in existing visual captioning models.

This work has been accepted to the European Conference on Computer Vision (ECCV), which takes place virtually August 23-28, 2020.

For more information on ML@GT at ECCV, visit our conference website.

Read the paper in full

Learning to Generate Grounded Visual Captions without Localization Supervision
Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira
Georgia Tech, NAVER LABS Europe, Facebook




Allie McFadden is the communications officer for the Machine Learning Center at Georgia Tech and the Constellations Center for Equity in Computing at Georgia Tech.
Allie McFadden is the communications officer for the Machine Learning Center at Georgia Tech and the Constellations Center for Equity in Computing at Georgia Tech.

Machine Learning Center at Georgia Tech




            AIhub is supported by:


Related posts :



2025 AI Index Report

  08 May 2025
Read the latest edition of the AI Index Report which tracks and visualises data related to AI.

Defending against prompt injection with structured queries (StruQ) and preference optimization (SecAlign)

  06 May 2025
Recent advances in LLMs enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them.

Forthcoming machine learning and AI seminars: May 2025 edition

  05 May 2025
A list of free-to-attend AI-related seminars that are scheduled to take place between 5 May and 30 June 2025.

Competition open for images of “digital transformation at work”

Digit and Better Images of AI have teamed up to launch a competition to create more realistic stock images of "digital transformation at work"
monthly digest

AIhub monthly digest: April 2025 – aligning GenAI with technical standards, ML applied to semiconductor manufacturing, and social choice problems

  30 Apr 2025
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.

#ICLR2025 social media round-up

  29 Apr 2025
Find out what participants got up to at the International Conference on Learning Representations.



 

AIhub is supported by:






©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence