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 28 for “"auxiliary task"”.
-
Using Machine Learning to Identify Functional Properties of Complex Systems: from Neurons to Networks
… activity of a neural population and perform an auxiliary task, hypothesized to be related the the function of those neurons. I find analytic conditions for when the inclusion of an auxiliary task can improve prediction of neural responses in a linear network, and derive an expression for the …
-
Natural language guided image and video understanding
… understanding and study several computer vision tasks at the intersection of vision and language. We first start the research with the challenging task of referring image segmentation. A dual convolutional LSTM network consisting of an encoder network and a decoder network is proposed to capture …
-
Reconstructing 3D Shapes as a Union of Boxes from Multi-View Images
… inference times. Additionally, we introduce an auxiliary task to aid in learning how to extract and transform spatial features from images without requiring camera calibrations. Extensive experiments demonstrate that our method can produce comparable results to approaches that require 3D …
-
A quest for label independence: from unsupervised annotation to self-supervised domain adaptation
… more labels. To this end, we focus on multi-tasked learning in ConvNets, and investigate how the main task can benefit from the auxiliary task, from a fully supervised multi-tasked scheme towards a self-supervised domain adaptation. In chapter 4, we dive into the skies and implement a …
-
Natural-language video description with deep recurrent neural networks
… describing what happened (in words) is an easy task. For machines, extracting meaning from video pixels and generating a sentence description is a very complex problem. The goal of this thesis is to develop models that can automatically generate natural language descriptions for events in …
-
Supervised-Unsupervised Cancer Subtyping Based on Multi-Task Learning
… framework by using the technique of multi-task learning. Specifically, we design a primary task of clustering and an auxiliary task of classification. By training the two tasks together, cancer-relevant subspaces and clusters are simultaneously learned. Within this strategy, we developed …
-
Multi-Task and Transfer Learning in Low-Resource Speech Recognition
… from a source domain during training, via Multi-Task Learning or Transfer Learning. With regards to Multi-Task Learning, Chapter (5) presents experiments which explicitly incorporate linguistic knowledge (i.e. phonetics and phonology) into an auxiliary task during neural Acoustic Model training. …
-
The Multimodal IMR-TrajNet - End-to-end Deep Ego Trajectory Prediction using Front-facing Camera Images and Standard Definition Maps
… the trajectories. Additionally, we introduced an auxiliary task to guide the model in learning more accurate trajectory shapes and utilized multimodal predictions to capture the inherent variability in possible driving paths. The results demonstrate a significant improvement in trajectory …
-
Stylistically Aware Representations of Books
… performance. Moreover, we find that adding an auxiliary task of genre classification to the primary task of success prediction improves results. Next, we propose a novel multimodal neural architecture that incorporates genre supervision to assign weights to individual feature types. As compared …
-
Knowledge transfer in vision tasks with incomplete data
… First, when transferring knowledge from previous tasks but the data used for training them is no longer available, we propose a method to extend and fine-tune the neural network to incorporate new classifiers while retaining the performance of existing classifiers. Second, with unsupervised domain …
-
Safety Risk Framework for Autonomous Driving Systems Under Perception Degradation
… on spatial and temporal features extracted from auxiliary task outputs of the model to determine expected Total Risk deviations from the Total Risk under nominal conditions. Activity 3 deploys the trained predictor for real-time safety degradation detection, enabling proactive intervention …
-
Multi-Task Learning For Deployable, Boundary-Refined Semantic Segmentation
Semantic segmentation is a task in computer vision that frequently employs convolutional neural networks (CNNs) to learn dense, pixel-wise object classification. Low-level feature preservation and robust, real-time network deployment are regarded as two of the biggest challenges in this task. The …
-
Continuous Speech Recognition for People with Dysarthria
… variability and the data scarcity make the task challenging. Moreover, the focus on dysarthric speech recognition research has not moved from isolated word to more challenging connected speech scenarios yet. There is a clear need to improve continuous dysarthric speech recognition. This …
-
Adapting Transformers for Structured Data Domains
… input representations, attention formulations, auxiliary tasks, prediction layers and loss functions - and adapt them to better suit the structure and semantics of specific data domains. Focusing on four structured domains - (i) sparse and irregularly sampled multivariate time-series, (ii) …
-
Improving vision-based robotic manipulation with affordance understanding
… in achieving goal-oriented robotic manipulation tasks. In this thesis, we focus on vision-based manipulation for real-time robotic application. A series of methods are proposed to improve the applicability for practical scenarios. Specifically we tackle the problem of identifying viable candidate …
-
Multi-task learning for leveraging noisy labels in automatic analysis of ultrasound images
… This thesis aims to investigate the use of multi-task learning to alleviate these issues, in the context of two problems. The first problem is echocardiographic video landmark detection, to quantify the dimensions of the left ventricle of the heart. We first propose a two-headed U-net-shaped …
-
Improving Video Highlight Detection via Unsupervised Learning and Test-Time Adaptation
… a TTA framework that uses a self-supervised auxiliary task, called cross-modality hallucinations, within a meta-auxiliary training scheme to improve both adaptation and highlight detection performance on unseen test videos. Extensive experiments and ablation studies on benchmark video …
-
A holistic deep learning framework for endoscopy
… different challenges in endoscopy. Various tasks can assist navigation, treatment planing and minimise missed lesions. Specifically, a novel bounding box pruning approach is proposed to improve artefact detection and an image quality assessment system based on artefact detection is …
-
EFFICIENT LOW-RESOURCE TRAINING WITH PRE-TRAINED DEEP NEURAL NETWORKS
… further trained (or fine-tuned) on downstream tasks. Nonetheless, the pre-trained deep neural networks are generally huge in size, e.g., with millions or billions of parameters, thus demanding abundant data and computation resources during fine-tuning. Therefore, it is of pragmatic merit to …
-
Domain Generalization and its Application in Deepfake Detection
… main loss via learnable parameters, for the TTT task, and we also suggest using additional adaptive parameters, which are the only updated parameters during the test phase, for the trained mode. By conducting experiments on different benchmarks, we show that the two ideas can both improve …
Page 1 of 2