Related papers: Diffusion-based Image Generation for In-distributi…

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…

This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion…

The performance of leaning-based perception algorithms suffer when deployed in out-of-distribution and underrepresented environments. Outdoor robots are particularly susceptible to rapid changes in visual scene appearance due to dynamic…

Generative diffusion models offer a natural choice for data augmentation when training complex vision models. However, ensuring reliability of their generative content as augmentation samples remains an open challenge. Despite a number of…

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. Currently, discriminator models outperform other methods in this regard. However, the feature extraction process used by…

We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…

Diffusion models are a special type of generative model, capable of synthesising new data from a learnt distribution. We introduce DISPR, a diffusion-based model for solving the inverse problem of three-dimensional (3D) cell shape…

Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose…

Recent advances in diffusion models have spurred research into their application for Reconstruction-based unsupervised anomaly detection. However, these methods may struggle with maintaining structural integrity and recovering the…

Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations like rotations and flips for generating extra data. However,…

The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion…

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their…

Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily…

We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data. The high cost of collecting and annotating data in the real-world has motivated the use of…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

Current perceptive models heavily depend on resource-intensive datasets, prompting the need for innovative solutions. Leveraging recent advances in diffusion models, synthetic data, by constructing image inputs from various annotations,…

Nuclei segmentation is a fundamental but challenging task in the quantitative analysis of histopathology images. Although fully-supervised deep learning-based methods have made significant progress, a large number of labeled images are…

In spite of recent progress, image diffusion models still produce artifacts. A common solution is to leverage the feedback provided by quality assessment systems or human annotators to optimize the model, where images are generally rated in…

Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored…