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 5 of 5 for “"Robust Image Classification"”.

  1. ROBUSTNESS AND UNCERTAINTY ESTIMATION FOR DEEP NEURAL NETWORKS

    … examples. This thesis focuses on improving the robustness against adversarial attacks and predictive uncertainty estimation of the existing DNN-based classification models. We first propose a new generative framework, called RBF-Net. We use the RBF-Net to develop a robust image classification …

    nus Repository record for ROBUSTNESS AND UNCERTAINTY ESTIMATION FOR DEEP NEURAL NETWORKS (opens in a new tab) Download file for ROBUSTNESS AND UNCERTAINTY ESTIMATION FOR DEEP NEURAL NETWORKS (opens in a new tab)

  2. Correlated Noise in Deep Convolutional Neural Networks

    … We provide empirical results on improved robust image classification in the setting of occluded and corrupted images. We then move on to studying the connection between popular dataset augmentation techniques and correlated variability. We compute a smooth estimate of the correlations of …

    waterloo Repository record for Correlated Noise in Deep Convolutional Neural Networks (opens in a new tab)

  3. TROPICAL GEOMETRIC APPROACHES TO DEEP LEARNING MODELS

    … with a piecewise linear logit layer for robust image classification with no additional parameters or computational complexity. Second, we introduce a Tropical Transformer which replaces the smooth softmax attention of traditional transformers with tropical attention and achieves superior …

    nps Repository record for TROPICAL GEOMETRIC APPROACHES TO DEEP LEARNING MODELS (opens in a new tab)

  4. Advancing Untrained Deep Neural Networks

    High-quality images are essential for many safety-critical and practical domains, ranging from commercial and medical to military applications. Nevertheless, real-world images are frequently degraded by nuisance factors, leading to noise, blur, and other distortions. Image restoration, the task of …

    umn Repository record for Advancing Untrained Deep Neural Networks (opens in a new tab)