Search Results for author:
Found 9 papers, 3 papers with code
ALOHa: A New Measure for Hallucination in Captioning Models
Despite recent advances in multimodal pre-training for visual description, state-of-the-art models still produce captions containing errors, such as hallucinating objects not present in a scene.
CLAIR: Evaluating Image Captions with Large Language Models
The evaluation of machine-generated image captions poses an interesting yet persistent challenge.
Simple Token-Level Confidence Improves Caption Correctness
The ability to judge whether a caption correctly describes an image is a critical part of vision-language understanding.
Ranked #62 on
Visual Reasoning
on Winoground
Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers
SPAN operates by regularizing attention masks from separate transformer heads to follow various priors over semantic regions.
Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
We first enable abstention capabilities for several VQA models, and analyze both their coverage, the portion of questions answered, and risk, the error on that portion.
On Guiding Visual Attention with Language Specification
To do this, we ground task-relevant words or phrases with attention maps from a pretrained large-scale model.
NBDT: Neural-Backed Decision Tree
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use.
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting.
NBDT: Neural-Backed Decision Trees
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use.
