Related papers: Multimodal Learning with Augmentation Techniques f…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

Reliable post-disaster building damage assessment (BDA) from satellite imagery is hindered by severe class imbalance, background clutter, and domain shift across disaster types and geographies. In this work, we address these problems and…

Clustering aims to group similar objects together while separating dissimilar ones apart. Thereafter, structures hidden in data can be identified to help understand data in an unsupervised manner. Traditional clustering methods such as…

We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…

Nowadays, misinformation articles, especially multimodal ones, are widely spread on social media platforms and cause serious negative effects. To control their propagation, Multimodal Misinformation Detection (MMD) becomes an active topic…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks. Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in…

Reliable machine learning and statistical analysis rely on diverse, well-distributed training data. However, real-world datasets are often limited in size and exhibit underrepresentation across key subpopulations, leading to biased…

The ability to track large-scale events as they happen is essential for understanding them and coordinating reactions in an appropriate and timely manner. This is true, for example, in emergency management and decision-making support, where…

Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and…

Low-quality or scarce data has posed significant challenges for training deep neural networks in practice. While classical data augmentation cannot contribute very different new data, diffusion models opens up a new door to build…

Scientific machine learning (SciML) increasingly requires models that capture multimodal conditional uncertainty arising from ill-posed inverse problems, multistability, and chaotic dynamics. While recent work has favored highly expressive…

Many single-target regression problems require estimates of uncertainty along with the point predictions. Probabilistic regression algorithms are well-suited for these tasks. However, the options are much more limited when the prediction…

Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms…

Denoising diffusion models (DDMs) have recently attracted increasing attention by showing impressive synthesis quality. DDMs are built on a diffusion process that pushes data to the noise distribution and the models learn to denoise. In…

The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study…

In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data…

In sequential recommendation systems, data augmentation and contrastive learning techniques have recently been introduced using diffusion models to achieve robust representation learning. However, most of the existing approaches use random…

Data scarcity is a primary obstacle in developing robust Machine Learning (ML) models for detecting rapidly intensifying tropical cyclones. Traditional data augmentation techniques (rotation, flipping, brightness adjustment) fail to…

Recent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation. However, while impressive progress has been made for teaching…