Related papers: Content-Style Identification via Differential Inde…
How to generate conditional synthetic data for a domain without utilizing information about its labels/attributes? Our work presents a solution to the above question. We propose a transfer learning-based framework utilizing normalizing…
Discrete diffusion models offer a flexible, controllable approach to structured sequence generation, yet they still lag behind causal language models in expressive power. A key limitation lies in their reliance on the Markovian assumption,…
We propose the conditional predictive impact (CPI), a consistent and unbiased estimator of the association between one or several features and a given outcome, conditional on a reduced feature set. Building on the knockoff framework of…
The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…
Identifying statistical dependence between the features and the label is a fundamental problem in supervised learning. This paper presents a framework for estimating dependence between numerical features and a categorical label using…
Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both…
With diverse presentation forgery methods emerging continually, detecting the authenticity of images has drawn growing attention. Although existing methods have achieved impressive accuracy in training dataset detection, they still perform…
We introduce a data-centric hypothesis-testing framework to quantify the influence of sequentially correlated literary properties--such as thematic continuity--on textual classification tasks. Our method models label sequences as stochastic…
It is commonplace to encounter heterogeneous or nonstationary data, of which the underlying generating process changes across domains or over time. Such a distribution shift feature presents both challenges and opportunities for causal…
The duality of content and style is inherent to the nature of art. For humans, these two elements are clearly different: content refers to the objects and concepts in the piece of art, and style to the way it is expressed. This duality…
A method for unsupervised contextual anomaly detection is proposed using a cross-linked pair of Variational Auto-Encoders for assigning a normality score to an observation. The method enables a distinct separation of contextual from…
Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed…
Causal structure learning with data from multiple contexts carries both opportunities and challenges. Opportunities arise from considering shared and context-specific causal graphs enabling to generalize and transfer causal knowledge across…
Synthesizing images from a given text description involves engaging two types of information: the content, which includes information explicitly described in the text (e.g., color, composition, etc.), and the style, which is usually not…
This work investigates the intersection property of conditional independence. It states that for random variables $A,B,C$ and $X$ we have that $X$ independent of $A$ given $B,C$ and $X$ independent of $B$ given $A,C$ implies $X$ independent…
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the…
Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent…
Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…
Balancing content fidelity and artistic style is a pivotal challenge in image generation. While traditional style transfer methods and modern Denoising Diffusion Probabilistic Models (DDPMs) strive to achieve this balance, they often…
In this paper, we propose a new evaluation metric called Domain Independence (DI) and Attenuation of Domain-Specific Information (ADSI) which is specifically designed for domain-generalized semantic segmentation in automotive images. DI…