RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in LVLMs.

Sangmin Woo Jaehyuk Jang Donguk Kim Yubin Choi Changick Kim

Published in: CoRR (2024)

Keyphrases

image transformations
rotation invariant
image analysis
input image
dictionary learning
image matching
low resolution
image features
object recognition
image registration
d objects
keypoints
facial images
texture descriptors
sift descriptors
pixel intensities
computer vision
image content
viewpoint