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"”.

  1. 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 …

    clemson Repository record for Gaslight: Attacking Hard-Label Black-Box Classifiers via Deep Reinforcement Learning (opens in a new tab)

  2. 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 …

    waterloo Repository record for Soft Labels for Training and Evaluating Semantic Segmentation Models (opens in a new tab)

  3. 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.

    houston Repository record for ADVERSARIAL ATTACKS ON MACHINE LEARNING MODELS USING FACE WARPING (opens in a new tab)

  4. 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, …

    colo-mines Repository record for Adversarial machine learning in computer vision: attacks and defenses on machine learning models (opens in a new tab)

  5. 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 …

    calpoly Repository record for Deep Learning for Affect Recognition: A Comparative Study of Physiological Sensor-Based and Facial Image-Based Approaches (opens in a new tab)

  6. 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 …

    ucf Repository record for Improving Efficiency in Deep Learning for Large Scale Visual Recognition (opens in a new tab)

  7. 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 …

    soton Download PDF for Efficient teacher-student architectures for Human Activity Recognition via soft labels and binarization (opens in a new tab)

  8. 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 …

    rit Repository record for Antidistillation Sampling for Classification Models (opens in a new tab)

  9. 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 …

    south-carolina Repository record for Deep Learning Models for Anomaly Detection in Industrial Inspection (opens in a new tab)