Related papers: P2T: Pyramid Pooling Transformer for Scene Underst…

Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pixelwise tasks has a…

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these…

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens…

Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often…

Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the…

Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis. While Transformers have…

Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword…

Multi-scale architecture, including hierarchical vision transformer, has been commonly applied to high-resolution semantic segmentation to deal with computational complexity with minimum performance loss. In this paper, we propose a novel…

Despite recent competitive performance across a range of vision tasks, vision Transformers still have an issue of heavy computational costs. Recently, vision prompt learning has provided an economic solution to this problem without…

Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the…

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on…

Spatial reasoning in 3D scenes requires precise geometric calculations that challenge vision-language models. Visual programming addresses this by decomposing problems into steps calling specialized tools, yet existing methods rely on…

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design…

Pain is a serious and costly issue globally, but to be treated, it must first be detected. Vision transformers are a top-performing architecture in computer vision, with little research on their use for pain detection. In this paper, we…

Action recognition models have achieved impressive results by incorporating scene-level annotations, such as objects, their relations, 3D structure, and more. However, obtaining annotations of scene structure for videos requires a…

The generalization of the Transformer architecture via MetaFormer has reshaped our understanding of its success in computer vision. By replacing self-attention with simpler token mixers, MetaFormer provides strong baselines for vision…

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

Recently, the advent of vision Transformer (ViT) has brought substantial advancements in 3D dataset benchmarks, particularly in 3D volumetric medical image segmentation (Vol-MedSeg). Concurrently, multi-layer perceptron (MLP) network has…