Related papers: Content-Style Identification via Differential Inde…

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed compared to purely discrete formulations. This gap is counterintuitive, given…

Semantic segmentation models trained on synthetic data often perform poorly on real-world images due to domain gaps, particularly in adverse conditions where labeled data is scarce. Yet, recent foundation models enable to generate realistic…

I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach,…

Recent Self-Supervised Learning (SSL) methods encapsulating relational information via masking in Graph Neural Networks (GNNs) have shown promising performance. However, most existing approaches rely on random masking strategies in either…

Bayesian networks provide a language for qualitatively representing the conditional independence properties of a distribution. This allows a natural and compact representation of the distribution, eases knowledge acquisition, and supports…

One of the challenges of handwriting recognition is to transcribe a large number of vastly different writing styles. State-of-the-art approaches do not explicitly use information about the writer's style, which may be limiting overall…

Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables,…

A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for…

Deep neural networks (DNNs) often struggle with out-of-distribution data, limiting their reliability in diverse realworld applications. To address this issue, domain generalization methods have been developed to learn domain-invariant…

Determining conditional independence (CI) relationships between random variables is a fundamental yet challenging task in machine learning and statistics, especially in high-dimensional settings. Existing generative model-based CI testing…

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive…

Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which…

Multi-source domain adaptation (MSDA) methods aim to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Although current methods achieve target joint distribution identifiability by enforcing minimal…

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the…

Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that this is not realistic as it is implausible to define the…

Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mimicking the…

Recently, image-to-image translation research has witnessed remarkable progress. Although current approaches successfully generate diverse outputs or perform scalable image transfer, these properties have not been combined into a single…

Music genre classification shapes how listeners discover music, how platforms design recommendations, and how sociologists study cultural taste. Yet existing genre labels are inconsistent in granularity: they exaggerate boundaries between…

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal…

As one of the prominent AI-generated content, Deepfake has raised significant safety concerns. Although it has been demonstrated that temporal consistency cues offer better generalization capability, existing methods based on CNNs…