Related papers: HAT: Hybrid Attention Transformer for Image Restor…

Pansharpening aims to enhance remote sensing image (RSI) quality by merging high-resolution panchromatic (PAN) with multispectral (MS) images. However, prior techniques struggled to optimally fuse PAN and MS images for enhanced spatial and…

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of…

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated…

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.…

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…

Single-pixel imaging (SPI) is a potential computational imaging technique which produces image by solving an illposed reconstruction problem from few measurements captured by a single-pixel detector. Deep learning has achieved impressive…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

A variety of attention mechanisms have been studied to improve the performance of various computer vision tasks. However, the prior methods overlooked the significance of retaining the information on both channel and spatial aspects to…

Medical image segmentation has made significant progress in recent years. Deep learning-based methods are recognized as data-hungry techniques, requiring large amounts of data with manual annotations. However, manual annotation is expensive…

This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vanilla vision transformers. To this end, we propose Hierarchical MHSA (H-MHSA), a novel approach that computes self-attention in…

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining…

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks…

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse…