Related papers: CFPFormer: Feature-pyramid like Transformer Decode…

Feature pyramid networks (FPN) are widely exploited for multi-scale feature fusion in existing advanced object detection frameworks. Numerous previous works have developed various structures for bidirectional feature fusion, all of which…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

Chronic wounds such as diabetic foot ulcers and pressure injuries require accurate tissue-level assessment to guide treatment planning and monitor healing progression. While deep learning methods have advanced automated wound analysis, most…

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and…

Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images. However, the current mainstream frequency-based pansharpening…

Convolutional Neural Networks (CNNs) have achieved promising results in medical image segmentation. However, CNNs require lots of training data and are incapable of handling pose and deformation of objects. Furthermore, their pooling layers…

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present…

Hyperspectral change detection (HCD) is one of the core applications of remote sensing images, holding significant research value in fields like environmental monitoring and disaster assessment. However, existing methods often suffer from…

Change detection (CD) in remote sensing aims to identify semantic differences between satellite images captured at different times. While deep learning has significantly advanced this field, existing approaches based on convolutional neural…

In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-attention is used in…

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Neuronal morphology encodes critical information about circuit function, development, and disease, yet current methods analyze topology or graph structure in isolation. We introduce GraPHFormer, a multimodal architecture that unifies these…

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip…

A novel Face Pyramid Vision Transformer (FPVT) is proposed to learn a discriminative multi-scale facial representations for face recognition and verification. In FPVT, Face Spatial Reduction Attention (FSRA) and Dimensionality Reduction…

Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…

In recent years, computer-aided diagnosis has become an increasingly popular topic. Methods based on convolutional neural networks have achieved good performance in medical image segmentation and classification. Due to the limitations of…

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross-attention mechanism…

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no…

Medical image segmentation is a critical aspect of modern medical research and clinical practice. Despite the remarkable performance of Convolutional Neural Networks (CNNs) in this domain, they inherently struggle to capture long-range…