Back to search

Rochester Institute of Technology

Advancing Multi-Modal Deep Learning: Towards Language-Grounded Visual Understanding

Abstract

dc:description.abstract

Using deep learning, computer vision now rivals people at object recognition and detection, opening doors to tackle new challenges in image understanding. Among these challenges, understanding and reasoning about language grounded visual content is of fundamental importance to advancing artificial intelligence. Recently, multiple datasets and algorithms have been created as proxy tasks towards this goal, with visual question answering (VQA) being the most widely studied. In VQA, an algorithm needs to produce an answer to a natural language question about an image. However, our survey of datasets and algorithms for VQA uncovered several sources of dataset bias and sub-optimal evaluation metrics that allowed algorithms to perform well by merely exploiting superficial statistical patterns. In this dissertation, we describe new algorithms and datasets that address these issues. We developed two new datasets and evaluation metrics that enable a more accurate measurement of abilities of a VQA model, and also expand VQA to include new abilities, such as reading text, handling out-of-vocabulary words, and understanding data-visualization. We also created new algorithms for VQA that have helped advance the state-of-the-art for VQA, including an algorithm that surpasses humans on two different chart question answering datasets about bar-charts, line-graphs and pie charts. Finally, we provide a holistic overview of several yet-unsolved challenges in not only VQA but vision and language research at large. Despite enormous progress, we find that a robust understanding and integration of vision and language is still an elusive goal, and much of the progress may be misleading due to dataset bias, superficial correlations and flaws in standard evaluation metrics. We carefully study and categorize these issues for several vision and language tasks and outline several possible paths towards development of safe, robust and trustworthy AI for language-grounded visual understanding.

Degree

thesis:*
Name thesis:degree_name
Imaging Science (Ph.D.)
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Chester F. Carlson Center for Imaging Science (COS)

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kafle, Kushal
Contributors dc:contributor
  • Christopher Kanan

Subjects

dc:subject × 5

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/10357

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kafle, Kushal. Advancing Multi-Modal Deep Learning: Towards Language-Grounded Visual Understanding. Dissertation thesis, https://repository.rit.edu/theses/10357