Results 1 to 10 of about 4,781,599 (116)
Rethinking the Inception Architecture for Computer Vision [PDF]
Computer Vision and Pattern Recognition, 2015 Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks.
Christian Szegedy +4 more
semanticscholar +5 more sources
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS [PDF]
Machine Learning and Knowledge Extraction, 2023 YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. We present a comprehensive analysis of YOLO’s evolution, examining the innovations and contributions in each iteration from the ...
Juan R. Terven +2 more
semanticscholar +1 more source
Attention mechanisms in computer vision: A survey [PDF]
Computational Visual Media, 2021 Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system.
Meng-Hao Guo +9 more
semanticscholar +1 more source
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [PDF]
IEEE International Conference on Computer Vision, 2021 This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such ...
Ze Liu +7 more
semanticscholar +1 more source
Masked Autoencoders Are Scalable Vision Learners [PDF]
Computer Vision and Pattern Recognition, 2021 This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs.
Kaiming He +5 more
semanticscholar +1 more source
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers [PDF]
Computer Vision and Pattern Recognition, 2022 Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate.
Dominik Zietlow +6 more
semanticscholar +1 more source
Vision Transformers in Medical Computer Vision - A Contemplative Retrospection [PDF]
arXiv.org, 2022 Recent escalation in the field of computer vision underpins a huddle of algorithms with the magnificent potential to unravel the information contained within images.
Arshi Parvaiz +5 more
semanticscholar +1 more source
IET Computer Vision, 2022 Despite recent advances in 3‐D pose estimation of human hands, thanks to the advent of convolutional neural networks (CNNs) and depth cameras, this task is still far from being solved in uncontrolled setups.
Meysam Madadi +3 more
doaj +1 more source
Mixed Differential Privacy in Computer Vision [PDF]
Computer Vision and Pattern Recognition, 2022 We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data.
Aditya Golatkar +5 more
semanticscholar +1 more source
The Programming Historian, 2022 This is the second of a two-part lesson introducing deep learning based computer vision methods for humanities research. This lesson digs deeper into the details of training a deep learning based computer vision model.
Daniel van Strien +4 more
doaj +1 more source