Browsing Theses by Supervisor "Veksler, Olga"
Now showing items 1-5 of 5
-
Occlusion-Ordered Semantic Instance Segmentation
(University of Waterloo, 2023-08-23)Conventional semantic ‘instance’ segmentation methods offer a segmentation mask for each object instance in an image along with its semantic class label. These methods excel in distinguishing instances, whether they belong ... -
Self-supervised Video Representation Learning by Exploiting Video Speed Changes
(University of Waterloo, 2022-04-29)In recent research, the self-supervised video representation learning methods have achieved improvement by exploring video’s temporal properties, such as playing speeds and temporal order. These works inspire us to exploit ... -
Test-Time Training for Image Inpainting
(University of Waterloo, 2022-06-21)Image inpainting is the task of filling missing regions in images with plausible and coherent content. The usual process involves training a CNN on a large collection of examples that it can learn from, to later apply this ... -
Volumetric Weak Supervision for Semantic Segmentation
(University of Waterloo, 2022-05-24)Semantic segmentation is a popular task in computer vision. Fully supervised methods are data hungry, they require pixel precise annotations for thousands of images. To reduce user annotation efforts, weak supervision for ... -
Weakly-supervised Semantic Segmentation with Regularized Loss Hyperparameter Search
(University of Waterloo, 2021-09-20)Weakly supervised segmentation signi cantly reduces user annotation e ort. Recently, regularized loss was proposed for single object class segmentation under image-level weak supervision. Regularized loss consists of ...