This paper examines the comparative effectiveness of a specialized compiled language
model and a general-purpose model like OpenAI's GPT-3.5 in detecting SDGs within text …

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual
representations. It uses pairs of augmentations of unlabeled training examples to define a …

In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability
to generate high-quality images from textual descriptions faces challenges with the potential …

As the field of deep learning experiences a meteoric rise, the urgency to decipher the
complex geometric properties of feature spaces, which underlie the effectiveness of diverse …

Synthetic data generation has become an emerging tool to help improve the adversarial
robustness in classification tasks, since robust learning requires a significantly larger …

Data augmentation has been proven effective for training high-accuracy convolutional
neural network classifiers by preventing overfitting. However, building deep neural networks …

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to
image classification systems, which is based on augmenting the training set with attacks that …

We show that label noise exists in adversarial training. Such label noise is due to the
mismatch between the true label distribution of adversarial examples and the label inherited …

Supervised learning methods trained with maximum likelihood objectives often overfit on
training data. Most regularizers that prevent overfitting look to increase confidence on …

We introduce a new defense against adversarial patch attacks based on our proposed
Robust Self-Attention (RSA) layer. Robust Self-Attention replaces the outlier-sensitive …