Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Given a long list of anomaly detection algorithms developed in the last few decades, how do
they perform with regard to (i) varying levels of supervision,(ii) different types of anomalies …

Real-world data often exhibits long tail distributions with heavy class imbalance, where the
majority classes can dominate the training process and alter the decision boundaries of the …

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as
CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit …

Multi-modal foundation models like OpenFlamingo, LLaVA, and GPT-4 are increasingly
used for various real-world tasks. Prior work has shown that these models are highly …

Vision-Language Pre-training (VLP) models have achieved remarkable success in practice,
while easily being misled by adversarial attack. Though harmful, adversarial attacks are …

Extracting generalized and robust representations is a major challenge in emotion
recognition in conversations (ERC). To address this, we propose a supervised adversarial …

Object detection plays a crucial role in scene understanding and has extensive practical
applications. In the field of remote sensing object detection, both detection accuracy and …

Abstract Adversarial training of Deep Neural Networks is known to be significantly more data-
hungry when compared to standard training. Furthermore, complex data augmentations …

The vulnerability of deep neural networks to imperceptible adversarial perturbations has
attracted widespread attention. Inspired by the success of vision-language foundation …