Search Results for author:
Found 9 papers, 0 papers with code
Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter
To tackle these challenges, first, we study the effective search space design for fine-tuning a VFM by comparing different operators (such as resolution, feature size, width, depth, and bit-widths) in terms of performance and BitOPs reduction.
PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality
Full DNN-based image signal processors (ISPs) have been actively studied and have achieved superior image quality compared to conventional ISPs.
Ranked #2 on
Image Enhancement
on MIT-Adobe 5k
(PSNR on proRGB metric)
Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection
To tackle these limitations, we propose a self-supervised reversed ISP method that does not require metadata and paired images.
Efficient Joint Detection and Multiple Object Tracking with Spatially Aware Transformer
We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture.
DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition
Image Signal Processors (ISPs) play important roles in image recognition tasks as well as in the perceptual quality of captured images.
Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments
We show that our proposed noise-accounted RAW augmentation method doubles the image recognition accuracy in challenging environments only with simple training data.
MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization
Our experiments demonstrated an improvement of 21 % for translation error and 26 % for orientation error on synthetic test data with respect to our previous work.
FOSS: Multi-Person Age Estimation with Focusing on Objects and Still Seeing Surroundings
Usually, such situations were solved by two separate models; one is a face detector model which crops facial regions and the other is an age estimation model which estimates from cropped images.
Single-Shot Pose Estimation of Surgical Robot Instruments' Shafts from Monocular Endoscopic Images
To avoid injuring the patients, a collision-avoidance algorithm that depends on having an accurate model for the poses of the instruments' shafts is used.
