Related papers: MDFL: Multi-domain Diffusion-driven Feature Learni…

Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs). However, the tens of thousands of patches in WSIs usually incur a vast…

Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…

Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when…

We introduce MxDiffusion, a hybrid physics- and data-driven diffusion-based framework that enables efficient and highly accurate generation of photonic structures from target optical properties. The improved accuracy is achieved through a…

With the rapid development of machine vision technology in recent years, many researchers have begun to focus on feature compression that is better suited for machine vision tasks. The target of feature compression is deep features, which…

Image restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods primarily focus on the spatial domain, neglecting the understanding of frequency variations and ignoring the impact of implicit…

Large language model hallucination represents a critical challenge where outputs deviate from factual accuracy due to distributional biases in training data. While recent investigations establish that specific hidden layers exhibit…

Diffusion models (DMs) have achieved promising performance in image restoration but haven't been explored for stereo images. The application of DM in stereo image restoration is confronted with a series of challenges. The need to…

Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level…

Multimode fibres (MMF) are remarkable high-capacity information channels owing to the large number of transmitting fibre modes, and have recently attracted significant renewed interest in applications such as optical communication, imaging,…

Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will encounter unreasonable object duplication and exponentially…

We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens to the input embeddings in the spatial domain, in this paper,…

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely…

Federated Learning (FL), as a distributed learning paradigm, trains models over distributed clients' data. FL is particularly beneficial for distributed training of Diffusion Models (DMs), which are high-quality image generators that…

Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

Driven by the new generation of multi-modal large models, such as Stable Diffusion (SD), image manipulation technologies have advanced rapidly, posing significant challenges to image forensics. However, existing image forgery localization…

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based…

Machine learning models are gaining increasing popularity in the domain of fluid dynamics for their potential to accelerate the production of high-fidelity computational fluid dynamics data. However, many recently proposed machine learning…

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this…