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 9 of 9 for “"Hard Label"”.
-
Gaslight: Attacking Hard-Label Black-Box Classifiers via Deep Reinforcement Learning
… into a predefined set of categories. With enough labeled data, a classifier can analyze an input’s components and calculate confidence scores for each category. However, machine learning relies heavily on approximation, which allows attackers to exploit classifiers by providing …
-
Soft Labels for Training and Evaluating Semantic Segmentation Models
… segmentation pipelines continue to rely on hard ground-truth labels and evaluation metrics originally designed for binary masks. This assumption is misaligned with real-world data, where object boundaries are often ambiguous, annotations are noisy, spatial downsampling aggregates multiple …
-
ADVERSARIAL ATTACKS ON MACHINE LEARNING MODELS USING FACE WARPING
… and gradients, but the target model provides hard-label predictions and confidence scores. Additionally, we would also be releasing a novel dataset consisting of celebrity images and warped images for researchers to use.
-
Adversarial machine learning in computer vision: attacks and defenses on machine learning models
… distinction under the formulation of multi-label classification to protect against adversarial examples. We also propose fuzzing-based hard-label black-box attacks against machine learning models. We design an AdvFuzzer to explore multiple paths between a source image and a guidance image, …
-
Deep Learning for Affect Recognition: A Comparative Study of Physiological Sensor-Based and Facial Image-Based Approaches
… approaches. The image-based component evaluates hard-label facial expression recognition on AffectNet+ using pre-trained ResNet-50, EfficientNet-B3, and ConvNeXt-Tiny architectures across Easy, Challenging, and Difficult subsets representing different levels of expression ambiguity. Experimental …
-
Improving Efficiency in Deep Learning for Large Scale Visual Recognition
… with the number of classes, a probabilistic label tree framework is proposed. A test sample is classified by traversing the label tree from the root node. Each node in the tree is associated with a probabilistic estimation of all the labels. The tree is learned recursively with iterative …
-
Efficient teacher-student architectures for Human Activity Recognition via soft labels and binarization
… first chapter of this report introduces a novel label representation for HAR in which we introduce the soft label shown to be capable of inducing better representation performance than that of the one-hot label. We will further investigate the teacher-student architecture for HAR. In our …
-
Antidistillation Sampling for Classification Models
… surrogate student models on the returned soft-label distributions. Antidistillation Sampling (ADS), recently proposed for large language models, perturbs the output distribution of a teacher model at inference time to degrade the quality of the resulting distilled model while preserving utility …
-
Deep Learning Models for Anomaly Detection in Industrial Inspection
… perception with limited supervision and strict hardware constraints. The first part of this dissertation presents a lightweight object detection model designed for rail component inspection under limited annotated labels and strict deployment hardware constrains. To address the challenges posed …