Related papers: Mind the Gap: Continuous Magnification Sampling fo…

Sampling from unnormalized densities using diffusion models has emerged as a powerful paradigm. However, while recent approaches that use least-squares `matching' objectives have improved scalability, they often necessitate significant…

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion…

To handle the large scale of whole slide images in computational pathology, most approaches first tessellate the images into smaller patches, extract features from these patches, and finally aggregate the feature vectors with…

The segmentation foundation model, e.g., Segment Anything Model (SAM), has attracted increasing interest in the medical image community. Early pioneering studies primarily concentrated on assessing and improving SAM's performance from the…

Radiologists rely on anatomical understanding to accurately delineate pathologies, yet most current deep learning approaches use pure pattern recognition and ignore the anatomical context in which pathologies develop. To narrow this gap, we…

Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation…

In addition to the intrinsic clustering of galaxies themselves, the spatial distribution of galaxies observed in surveys is modulated by the presence of weak lensing due to matter in the foreground. This effect, known as magnification bias,…

Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge for computational pathology, hindering cross-batch generalization and limiting reliable…

Sampling is a widely used graph reduction technique to accelerate graph computations and simplify graph visualizations. By comprehensively analyzing the literature on graph sampling, we assume that existing algorithms cannot effectively…

Despite the impressive performance across a wide range of applications, current computational pathology models face significant diagnostic efficiency challenges due to their reliance on high-magnification whole-slide image analysis. This…

Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image synthesis compared to…

The best practical techniques for exact solution of instances of the constrained maximum-entropy sampling problem, a discrete-optimization problem arising in the design of experiments, are via a branch-and-bound framework, working with a…

Developing a suitable Deep Neural Network (DNN) often requires significant iteration, where different model versions are evaluated and compared. While metrics such as accuracy are a powerful means to succinctly describe a model's…

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical…

A critical challenge for tumour segmentation models is the ability to adapt to diverse clinical settings, particularly when applied to poor-quality neuroimaging data. The uncertainty surrounding this adaptation stems from the lack of…

Medical image segmentation models struggle with rare abnormalities due to scarce annotated pathological data. We propose DiffAug a novel framework that combines textguided diffusion-based generation with automatic segmentation validation to…

This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors. Other state-of-theart works mainly focus on fully supervised…

Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the…

Pathology image segmentation across multiple centers encounters significant challenges due to diverse sources of heterogeneity including imaging modalities, organs, and scanning equipment, whose variability brings representation bias and…