Search
Skip to Search Results- 19Ray, Nilanjan (Computing Science)
- 5Zhang, Hong (Computing Science)
- 1Boulanger, Pierre (Computing Science)
- 1Erbilgin, Nadir (Renewable Resources)
- 1Schubert, Matthias (Institute for Informatic, Ludwig-Maximilians-Universität München)
- 1Tennant, Matthew (Medicine)
- 1Aziz, Muhammad Usman
- 1Bahri, Fateme
- 1Elkerdawy, Sara
- 1Foroughi, Homa
- 1Guruprasad, Namitha
- 1Kapil, Rudraksh
- 4Computer Vision
- 3Deep Learning
- 3Model Compression
- 2Image Registration
- 2Medical Imaging
- 2Object detection
-
Fall 2023
Histological examination and derived ancillary testing remain the gold standard for breast cancer diagnosis, prognosis assessment and treatment guidance. Currently, a commercial molecular signature test OncotypeDX®, based on RNA quantitation and providing a recurrence score (RS) ranging from 0 to...
-
Advancing Forest Health Monitoring: Harnessing the Power of Deep Learning Computer Vision for Remote Sensing Applications
DownloadFall 2023
Forests provide immense economic, ecological, and societal values, making forest health monitoring (FHM) a crucial task for guiding conservation and management of these essential ecosystems. Drones have seen increased popularity in this domain due to their ability to collect high-resolution,...
-
Spring 2023
Predicting a dense depth map from LiDAR scans and synced RGB images with a small deep neural network is a challenging task. Most top-accuracy methods boost precision by having a very large number of parameters and as a result huge memory consumption. Whereas, depth completion tasks are commonly...
-
Computing Velocity of Multiple Objects in Sequences of Images With an Application In Water-Based Bitumen Extraction Process
DownloadSpring 2017
Image-based analysis of bitumen extraction process can provide the oil companies with useful information that can be used to assess their performance in retrieving bitumen from the oil sands. In this analysis, several slurry images are taken during the extraction process, and then image...
-
Fall 2023
Recent work has shown that by approximating the behaviour of a non-differentiable black-box function using a neural network, the black-box can be integrated into a differentiable training pipeline for end-to-end training. This methodology is termed "differentiable bypass," and a successful...
-
Extending Differentiable Programming to include Non-differentiable Modules using Differentiable Bypass for Combining Convolutional Neural Networks and Dynamic Programming into an End-to-end Trainable Framework
DownloadSpring 2019
Differentiable Programming is the paradigm where different functions or modules are combined into a unified pipeline with the purpose of applying end-to-end learning or optimization. A natural impediment is the non-differentiability characteristic of many modules. This thesis proposes a new way...
-
Image Registration with Homography: A Refresher with Differentiable Mutual Information, Ordinary Differential Equation and Complex Matrix Exponential
DownloadFall 2020
This work presents a novel method of tackling the task of image registration. Our algorithm uses a differentiable form of Mutual Information implemented via a neural network called MINE. An important property of neural networks is them being differentiable, which allows them to be used as a loss...
-
Spring 2017
At the core of many computer vision methods lies the question of how to represent data. Representing the data in a meaningful way, which highlights its most useful properties, can significantly affect the performance of any vision-based application. Traditional systems are heavily reliant on...
-
Spring 2023
Diffeomorphic image registration is important for medical imaging studies because of the properties like invertibility, smoothness of the transformation, and topology preservation/non-folding of the grid. Violation of these properties can lead to destruction of the neighbourhood and the...
-
Mixed Low-bit Quantization for Model Compression with Layer Importance and Gradient Estimations
DownloadSpring 2022
Deep neural networks (DNNs) have been widely used in the modern world in recent years. However, due to the substantial memory consumption and high computational power use of DNNs, deploying them on devices with limited resources is challenging. Model compression methods can provide us with a...