Related papers: Denoised Diffusion for Object-Focused Image Augmen…

Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of various data-scarce tasks. With the powerful image generation…

Training robust learning algorithms across different medical imaging modalities is challenging due to the large domain gap. Unsupervised domain adaptation (UDA) mitigates this problem by using annotated images from the source domain and…

Boundary detection of irregular and translucent objects is an important problem with applications in medical imaging, environmental monitoring and manufacturing, where many of these applications are plagued with scarce labeled data and low…

Medical image segmentation is crucial for accurate clinical diagnoses, yet it faces challenges such as low contrast between lesions and normal tissues, unclear boundaries, and high variability across patients. Deep learning has improved…

Animal pose estimation is a fundamental task in computer vision, with growing importance in ecological monitoring, behavioral analysis, and intelligent livestock management. Compared to human pose estimation, animal pose estimation is more…

Single-Domain Generalized Object Detection~(S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on…

Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This…

Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it…

Accurate single cell detection in brightfield microscopy is crucial for biological research, yet data scarcity and annotation bottlenecks limit the progress of deep learning methods. We investigate the use of unconditional models to…

Precision agriculture involves the application of advanced technologies to improve agricultural productivity, efficiency, and profitability while minimizing waste and environmental impact. Deep learning approaches enable automated…

Due to network operation and maintenance relying heavily on network traffic monitoring, traffic matrix analysis has been one of the most crucial issues for network management related tasks. However, it is challenging to reliably obtain the…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

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…

Training-free diffusion models have achieved remarkable progress in generating multi-subject consistent images within open-domain scenarios. The key idea of these methods is to incorporate reference subject information within the attention…

High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity images due to their inability to adequately capture morphological details, which may affect…

Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high…

Magnetic resonance (MR) imaging, including cardiac MR, is prone to domain shift due to variations in imaging devices and acquisition protocols. This challenge limits the deployment of trained AI models in real-world scenarios, where…

Although the availability of a large amount of data is usually given for granted, there are relevant scenarios where this is not the case; for instance, in the biomedical/healthcare domain, some applications require to build huge datasets…

Existing unsupervised low-light image enhancement methods lack enough effectiveness and generalization in practical applications. We suppose this is because of the absence of explicit supervision and the inherent gap between real-world…

Although learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing…