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 10 of 10 for “"Feature disentanglement"”.
-
Domain adaptive learning with disentangled features
… loss. These models align the domain-specific feature distribution and the domain-invariant feature distribution simultaneously, which is sub-optimal towards solving deep domain adaptation tasks, given that deep neural networks are known to extract features in which multiple hidden factors are …
-
Controllable human image synthesis and editing
… additional complexity from unsupervised feature disentanglement. Moreover, another significant challenge in this field is striking the optimal balance between texture control and overall image quality preservation. Manipulating clothing textures to match given conditions, such as new …
-
Experimental Characterisation of Molecular Junctions Via Scanning Probe Microscopy
… a detailed investigation of autoencoder-based feature extraction and clustering algorithms was conducted. Notably, the role of feature disentanglement in STMBJ data segmentation was studied for the first time. Additionally, a high-precision thermovoltage AFM (ThAFM) module was developed which …
-
Intelligent Fault Diagnosis and Health State Recognition of Rotating Machinery Under Variable Working Conditions Using Deep Transfer Learning
… source domain and a target domain share similar feature distributions, an assumption that rarely holds under variable working conditions in industrial settings. Transfer learning mitigates distribution discrepancies, yet important challenges remain: (1) effective IFD under changing operating …
-
Improving Content-Aware Recommendation: Relationship Mining, Integrating, and Disentangling
… is to disentangle the content and collab-orative features to address the duplication problem in content-aware recommendations. We propose a novel two-level disentanglement approach that supports both content-collaborative disentanglement and feature disentanglement based on a variational …
-
Understanding Videos by Learning Structured, Robust and Efficient Representations
… involves multiple facets such as structural feature learning, modeling motion, multi-modal feature learning, feature disentanglement etc., with the primary goal of holistic video understanding. Recently, self-supervised learning has gained prominence as an effective paradigm for …
-
Contrastive Modeling and Signal Representation for Anomaly Detection and Diagnosis
… classification frame-work that resolves the feature collapse issue during training. This is complemented by a learnable feature augmentation strategy within the proposed One-Class Con-trastive Reconstruction Framework (OCCRF), which supports GPU-efficient de-ployment and surpasses both …
-
MODELING ADAPTABILITY MECHANISMS OF SPEECH PERCEPTION Nika Jurov
… rely more on some speech cues (or also called features or dimensions) than others, it is yet not understood how listeners weight them flexibly on a moment-to-moment basis when the input might deviate from the standard speech. This thesis computationally explores flexible cue re-weighting as an …
-
Deep Learning Characterization and Mechanical Ranking of Microstructure Features in Geomaterials
… the relative importance of microstructure features on local field variables, such as the stress field. Here, 2D composite materials made of a solid matrix and cracks are modeled numerically with the Finite Element Method (FEM) and cohesive zone models (CZM). A Non-Linear Variational …
-
Visual Representation Learning with Progressive Data Scarcity.
… network does not rely directly on hand-crafted features. There is no denying that the availability of large-scale annotated data plays a vital role in the success of deep learning, among many other others. On the other hand, given the capacity of deep neural networks, modern deep learning system …