Browsing Computer Science by Author "Tang, Meng"
Now showing items 1-2 of 2
-
Constrained-CNN losses for weakly supervised segmentation
Kervadec, Hoel; Dolz, Jose; Tang, Meng; Granger, Eric; Boykov, Yuri; Ben Ayed, Ismail (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. ... -
Optimization for Image Segmentation
Tang, Meng (University of Waterloo, 2019-06-26)Image segmentation, i.e., assigning each pixel a discrete label, is an essential task in computer vision with lots of applications. Major techniques for segmentation include for example Markov Random Field (MRF), Kernel ...