Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 224 for “"Deep networks"”.
-
Video Understanding with Deep Networks
… additionally used. Encouraged by the success of deep convolutional neural networks (CNNs) on image classification, we extend the deep convolutional networks to video understanding by modeling both spatial and temporal information. To effectively utilize deep networks, we need a comprehensive …
-
Efficient Deep Networks for Image Matting
… a nity is widely used in both traditional and deep matting methods, we propose upsampling operators conditioned on the second-order a nity information, termed a nity-aware upsampling. Instead of modeling a nity in an additional module, we include it in the unavoidable upsampling stages for a …
-
Hierarchical Decomposition of Large Deep Networks
… as pose, occlusions and image fidelity. Recent deep learning approaches in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) are built using very large and deep convolution neural network architectures. In 2015, such architectures outperformed human performance (94.9% human vs …
-
Spatial Deep Networks for Outdoor Scene Classification
… been leveraged in conjunction with convolutional networks to perform classification tasks. In the existing approach, one random patch is extracted from each training image to learn filters for convolutional processes. However, feature learning only from one random patch per image is not robust …
-
Modeling Human Visual Detection Using Deep Networks
… images to detect objects. To accomplish this, deep learning architectures designed for image classification are adapted, extending these architectures to predict detection statistics of human observers.
-
Constrained deep networks for medical image segmentation
… need for laborious pixel annotations required by deep learning models. Enforcing high-order, global inequality constraints on the network outputs can leverage unlabeled data by guiding the training with prior knowledge, restricting the search space during training to anatomically feasible …
-
Advanced Music Audio Feature Learning with Deep Networks
… audio signals, this research analyzes the use of deep network structures for extracting features from musical audio data represented in the frequency domain. Image-based network models are designed to be robust and accurate learners of image features. As such, this research develops image-based …
-
IMPROVED TRAINING OF DEEP NETWORKS FOR COMPUTER VISION
Deep neural networks have become the state-of-the-art tool to solve many computer vision problems. However, these algorithms face a lot of computational and optimization challenges. For example, a) the training of deep networks is not only computationally intensive but also requires a lot of manual …
-
Adversarial Vulnerabilities of Deep Networks and Affordable Robustness
Deep learning has improved the performance of many computer vision tasks. However, the features that are learned without extra regularization are not necessarily interpretable. While in terms of generalization, conventionally trained models seem to perform really well, they are susceptible to …
-
A study of interpretability mechanisms for deep networks
<p>Deep neural networks are traditionally considered to be “black-box” models where it is generally difficult to interpret a certain decision made by such models given a test instance. However, as deep learning is increasingly becoming the tool of choice in making many safety-critical and …
-
Understanding Representations and Reducing their Redundancy in Deep Networks
Neural networks in their modern deep learning incarnation have achieved state of the art performance on a wide variety of tasks and domains. A core intuition behind these methods is that they learn layers of features which interpolate between two domains in a series of related parts. The first part …
-
NON-STATIONARY PROCESSING IN DEEP NETWORKS FOR EFFICIENT MULTIMEDIA APPLICATIONS
Deep neural networks (DNNs) have revolutionized multimedia applications, including computer vision, audio processing, and natural language processing. However, traditional DNNs rely on stationary processing, where convolutional or linear operations uniformly handle features across spatial and …
-
Everything Efficient All at Once - Compressing Data and Deep Networks
In this thesis, we examine the efficiency of deep networks and data, both of which are widely used in various computer vision/AI applications and are ubiquitous in today's information age. As deep networks continue to grow exponentially in size, improving their efficiency in terms of size and …
-
Identifying facial landmarks, action units and emotions using deep networks
The goal of this thesis it to use deep neural networks, specifically Convolutional Neural Networks (CNNs) to predict facial landmarks, facial action units and emotions and to study the results of intermediate experiments while doing so. Learning the different features of facial images has always …
-
An Investigation of Scale Factor in Deep Networks for Scene Recognition
… there a significant difference in the design of deep networks for the tasks of classifying object-centric images and scenery images? How to design networks that extract the most representative features for scene recognition? To answer these questions, we design studies to examine the scales and …
-
Can We Gain More from Orthogonality Regularizations in Training Deep Networks?
… is found to be a favorable property for training deep convolutional neural networks, how we can enforce it in more effective and easy-to-use ways? Through this work we look to come up with novel orthogonality regularizations for training deep CNNs, utilizing various advanced analytical tools such …
-
The implicit bias of gradient descent: from linear classifiers to deep networks
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping
… illustrate the idea of using synthetic data and deep networks to recognize primitive shapes for facilitating object grasping. A segmentation-based architecture is proposed to decompose objects into multiple primitive shapes from monocular depth input for robotic manipulation. The backbone deep …
-
From Graph Theory for Robust Deep Networks to Graph Learning for Multimodal Cancer Analysis
… explores the intersection of graph theory and deep learning, focusing on enhancing the robustness of deep neural networks (DNNs) and applying these advancements to complex problems like cancer diagnosis and treatment. We investigate the structural properties of graphs and their influence on …
Page 1 of 12