Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection.

Yuxin Fang Shusheng Yang Shijie Wang Yixiao Ge Ying Shan Xinggang Wang

Published in: ICCV (2023)

Keyphrases

object detection
image data
input image
computer vision
scene understanding
single image
image representation
image analysis
image features
image retrieval
image classification
image segmentation
multiscale
segmentation algorithm
image pixels
image content
low level
face detection
image regions
vision system
feature points
high resolution
fuzzy logic
object recognition
edge detection
region of interest
image structure
denoising
multi class