Recent advances on loss functions in deep learning for computer vision
The loss function, also known as cost function, is used for training a neural network or other
machine learning models. Over the past decade, researchers have designed many loss …
machine learning models. Over the past decade, researchers have designed many loss …
Recent trends and advances in fundus image analysis: A review
Automated retinal image analysis holds prime significance in the accurate diagnosis of
various critical eye diseases that include diabetic retinopathy (DR), age-related macular …
various critical eye diseases that include diabetic retinopathy (DR), age-related macular …
Unifying flow, stereo and depth estimation
We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …
Learning to estimate hidden motions with global motion aggregation
Occlusions pose a significant challenge to optical flow algorithms that rely on local
evidences. We consider an occluded point to be one that is imaged in the first frame but not …
evidences. We consider an occluded point to be one that is imaged in the first frame but not …
Siamese masked autoencoders
Establishing correspondence between images or scenes is a significant challenge in
computer vision, especially given occlusions, viewpoint changes, and varying object …
computer vision, especially given occlusions, viewpoint changes, and varying object …
Cotr: Correspondence transformer for matching across images
We propose a novel framework for finding correspondences in images based on a deep
neural network that, given two images and a query point in one of them, finds its …
neural network that, given two images and a query point in one of them, finds its …
Rethinking RGB-D salient object detection: Models, data sets, and large-scale benchmarks
The use of RGB-D information for salient object detection (SOD) has been extensively
explored in recent years. However, relatively few efforts have been put toward modeling …
explored in recent years. However, relatively few efforts have been put toward modeling …
Voxelmorph: a learning framework for deformable medical image registration
We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical
image registration. Traditional registration methods optimize an objective function for each …
image registration. Traditional registration methods optimize an objective function for each …
Learning correspondence from the cycle-consistency of time
We introduce a self-supervised method for learning visual correspondence from unlabeled
video. The main idea is to use cycle-consistency in time as free supervisory signal for …
video. The main idea is to use cycle-consistency in time as free supervisory signal for …