Browsing Waterloo Research by Subject "deep learning"
Now showing items 1-4 of 4
-
Constrained-CNN losses for weakly supervised segmentation
(Elsevier, 2019-05)Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. ... -
A First Look at Generating Website Fingerprinting Attacks via Neural Architecture Search
(Workshop on Privacy in the Electronic Society, 2023-11-26)An adversary can use website fingerprinting (WF) attacks to breach the privacy of users who access the web through encrypted tunnels like Tor. These attacks have increasingly relied on the use of deep neural networks (DNNs) ... -
Global-connected network with generalized ReLU activation
(Elsevier, 2019-12)Recent Progress has shown that exploitation of hidden layer neurons in convolutional neural networks (CNN) incorporating with a carefully designed activation function can yield better classification results in the field ... -
Line-based deep learning method for tree branch detection from digital images
(Elsevier, 2022-06)Preventive maintenance of power lines, including cutting and pruning of tree branches, is essential to avoid interruptions in the energy supply. Automatic methods can support this risky task and also reduce time consuming. ...