Related papers: Swin3D: A Pretrained Transformer Backbone for 3D I…

Medical image segmentation is a critical task in clinical workflows, particularly for the detection and delineation of pathological regions. While convolutional architectures like U-Net have become standard for such tasks, their limited…

Most deep learning backbones are evaluated on ImageNet. Using scenery images as an example, we conducted extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences…

Deep neural networks (DNNs) have achieved the state of the art performance in numerous fields. However, DNNs need high computation times, and people always expect better performance in a lower computation. Therefore, we study the human…

The emerging technology of snapshot compressive imaging (SCI) enables capturing high dimensional (HD) data in an efficient way. It is generally implemented by two components: an optical encoder that compresses HD signals into a 2D…

We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or…

X-ray Photoelectron Spectroscopy (XPS) is a crucial technique for material surface analysis, yet interpreting its spectra is often challenging for both human analysts and automated methods due to the prevalence of variable spectral shifts…

Achieving 3D spatial awareness is crucial for surgical robotic manipulation, where precise and delicate operations are required. Existing methods either explicitly reconstruct the surgical scene prior to manipulation, or enhance multi-view…

Medical image segmentation is a crucial task in the field of medical image analysis. Harmonizing the convolution and multi-head self-attention mechanism is a recent research focus in this field, with various combination methods proposed.…

In this study, we proposed a deep Swin-Vision Transformer-based transfer learning architecture for robust multi-cancer histopathological image classification. The proposed framework integrates a hierarchical Swin Transformer with…

This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks. Especially for…

Accurate spatio-temporal prediction is crucial for the sustainable development of smart cities. However, current approaches often struggle to capture important spatio-temporal relationships, particularly overlooking global relations among…

A deep learning-assisted inversion method is proposed to solve the inhomogeneous background imaging problem. Three non-iterative methods, namely the distorted-Born (DB) major current coefficients method, the DB modified Born approximation…

Skull stripping is a common preprocessing step that is often performed manually in Magnetic Resonance Imaging (MRI) pipelines, including functional MRI (fMRI). This manual process is time-consuming and operator dependent. Automating this…

3D neural networks have become prevalent for many 3D vision tasks including object detection, segmentation, registration, and various perception tasks for 3D inputs. However, due to the sparsity and irregularity of 3D data, custom 3D…

Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…

The recent 3D medical ViTs (e.g., SwinUNETR) achieve the state-of-the-art performances on several 3D volumetric data benchmarks, including 3D medical image segmentation. Hierarchical transformers (e.g., Swin Transformers) reintroduced…

Human can infer the 3D geometry of a scene from a sketch instead of a realistic image, which indicates that the spatial structure plays a fundamental role in understanding the depth of scenes. We are the first to explore the learning of a…

In recent years, Vision Transformer-based approaches for low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of…

Face super-resolution aims to recover high-quality facial images from severely degraded low-resolution inputs, but remains challenging due to the loss of fine structural details and identity-specific features. This work introduces SwinIFS,…

Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume…