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 25 for “"Consistency Regularization"”.
-
Randomized dimension reduction with statistical guarantees
… sample complexity analysis for data augmentation consistency regularization where we view sample efficiency from the lens of dimension reduction in the function space. Then in Chapter 5, we introduce an adaptively weighted data augmentation consistency regularization algorithm for distributionally …
-
Towards Accurate Semi-Supervised Semantic Segmentation with Fewer Annotations
… catastrophic forgetting. First, we propose a new consistency regularization framework, termed mutual knowledge distillation (MKD), combined with data and feature augmentation. We introduce two auxiliary mean-teacher models based on consistency regularization. More specifically, we use the …
-
Weakly Supervised Learning for Musical Instrument Classification
… model. The final method is based on consistency regularization-based SSL. The method proposed uses the mean teacher model, where a teacher model maintains a moving average or low-pass filtered version of a student model. The consistency regularization loss is unsupervised and may thus …
-
Deep Semi-Supervised Learning Methodologies and Applications
… semi-supervised method by upgrading the consistency regularization popular in many semi-supervised methods to a stronger regularization, i.e., heterogeneous classifier consistency regularization. Such a regularization is effective in regularizing the feature extractor and helps knowledge …
-
Understanding and Improving Generative Adversarial Networks in Low-Data Settings
… GAN stability. Chapter 3 presents a novel regularization technique using noise modulation on discriminator feature to prevent discriminator overfitting, and using consistency regularization to reduce gradient explosion and stabilize training. Chapter 4 proposes a Lipschitz-constrained …
-
Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization
… to maximize global performance via a novel consistency regularization loss between individual utility and a global action-value function. Experiments on diverse road topologies and traffic flow conditions in the SUMO traffic simulator show competitive performance of QCOMBO versus recent …
-
Towards Improving Generalization of Multi-Task Learning
… adaptive AMTRL method and a novel representation consistency regularization-based Semi-MTL method are proposed respectively. As to the between-task competition, this thesis analyzes the task variance and task imbalance; furthermore, a novel task variance regularization-based MTL method and a novel …
-
Exploring semi-supervised methods in magnetic resonance imaging analysis /
… prominent semi-supervised methods, namely consistency regularization, pseudo-labeling, co-training, contrastive learning, adversarial learning, and hybrid methods. Comparative experiments were conducted, with techniques including Mean Teacher (MT), Deep Adversarial Networks (DAN), …
-
Adaptive and weighted optimization for efficient and robust learning
… On top of AdaLoss, we enhance data augmentation consistency regularization with an adaptively weighted schedule (\ours) using loss information to handle volumetric medical image segmentation with both sparsely labeled and densely labeled slices. We evaluate our method on CT and MRI scans and …
-
Efficient Spatiotemporal Representation Learning Techniques for Videos and Remote Sensing Data
… for unsupervised change detection, cross-consistency regularization for semi-supervised change direction, hierarchical transformer networks for change detection and pansharpening, spatial and interaction space graph reasoning for road detection, and deep image prior coupled with …
-
Towards Label-Efficient Approaches For Dense Video Tasks
… framework for video action detection using consistency regularization, where a model learns stable predictions across augmented views of the same video. This is challenging, generic augmentations often affect only static regions, providing limited information about dynamic actions. We …
-
Few-Shot Medical Image Segmentation Using Semi-Supervised and Weakly-Supervised Learning
… segmentation method inspired by the idea of consistency regularization and by creating redundant complementing labels. 5- We introduce a semi-supervised learning method for the segmentation of any medical image by designing a novel loss function. The loss function incorporates an adaptation …
-
Επαναληπτικός καθαρισμός προβλέψεων για ημι-επιβλεπόμενη μάθηση
… κανονικοποίησης συνέπειας και ψευδο-εμβάπτισης(consistency regularization and pseudo-labeling) ακολουθώντας το FixMatch και (2) αύξηση του σετ ετικετών με τα επιλεγμένα παραδείγματα του πρώτου σταδίου και ημι-επιβλεπόμενη εκπαίδευση με βάση το FixMatch στο επαυξημένο σύνολο δεδομένων. Το …
-
Annotation-efficient and reliable medical image segmentation
… By applying box-based spatial constraints and consistency regularization to compensate for the reduced label information, our approach avoids costly pixel-level supervision during training and enables resource-efficient segmentation. Results show that weakly-supervised prompt learning is a …
-
Weakly-supervised learning in Computer Vision and Medical Imaging
… such as semi-supervised learning focus on consistency regularization and explore various data augmentation strategies. However, in real-world scenarios such as Medical Image Analysis (MIA), these methods fail with severe class imbalance. Moreover, few methods have been tested under a …
-
Multiclass Misleading News Classification
… input trained using cross-entropy loss, R-Drop consistency regularization, and label-preserving augmentation. The methods were evaluated on LIAR2 and PolitiFact Fact Check under matched with and without justification conditions. On LIAR2 with justification, LMNC achieved 71.91% accuracy and …
-
Discriminative Feature Learning with Application to Fine-grained Recognition
… from the same class by introducing a label consistency regularization. This label consistency constraint makes the features more discriminative and tends to faster convergence. The third part proposes a more sophisticated and effective end-to-end network specifically designed for …
-
Towards Generalizable Representation Learning Across Domains
… augmentation strategy called Fo-Mixup and a dual consistency regularization that encourages consistent local and global representations. This leads to more robust and generalizable deepfake detection. For vision-language recognition, this thesis introduces Style-Pro, a style-guided prompt learning …
-
Reducing the effort for data annotation
… of recent research on self-training, entropy regularization, consistency regularization, and hybrid approaches. The goal of semi-supervised learning is to train machine learning models on a small dataset of annotated training data while simultaneously using a larger dataset of completely …
Page 1 of 2