Related papers: CoDi: Co-evolving Contrastive Diffusion Models for…

Contrastive learning has been effectively utilized to enhance the training of sequential recommendation models by leveraging informative self-supervised signals. Most existing approaches generate augmented views of the same user sequence…

Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores whether synthetic tabular data can be reliably identified ''in…

Recent literature has effectively leveraged diffusion models trained on continuous variables as priors for solving inverse problems. Notably, discrete diffusion models with discrete latent codes have shown strong performance, particularly…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…

Existing neural methods have shown great potentials towards generating informative text from structured tabular data as well as maintaining high content fidelity. However, few of them shed light on generating personalized expressions, which…

Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven…

Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted extensive attention in recent years. Currently, the majority of…

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or…

Contrastive learning methods in computer vision typically rely on augmented views of the same image or multimodal pretraining strategies that align paired modalities. However, these approaches often overlook semantic relationships between…

We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference time. The individual models can be trained in isolation, at…

Tabular data synthesis is a long-standing research topic in machine learning. Many different methods have been proposed over the past decades, ranging from statistical methods to deep generative methods. However, it has not always been…

Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent…

Polyp detection is crucial for colorectal cancer screening, yet existing models are limited by the scale and diversity of available data. While generative models show promise for data augmentation, current methods mainly focus on enhancing…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

We provide an overview of the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in…

Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This…

Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts. It is tempting to use these systems to eliminate the manual task of…

Counterfactual explanations methods provide an important tool in the field of {interpretable machine learning}. Recent advances in this direction have focused on diffusion models to explain a deep classifier. However, these techniques have…

Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. The former relies on the true…