Related papers: Efficient Mixed Transformer for Single Image Super…
The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing…
Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct…
Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical…
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI). These CNN-based methods…
Multi-image super-resolution (MISR) can achieve higher image quality than single-image super-resolution (SISR) by aggregating sub-pixel information from multiple spatially shifted frames. Among MISR tasks, burst super-resolution (BurstSR)…
Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing…
Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…
Backprojection networks have achieved promising super-resolution performance for nature images but not well be explored in the remote sensing image super-resolution (RSISR) field due to the high computation costs. In this paper, we propose…
Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less…
The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still…
Facial expression recognition (FER) has received considerable attention in computer vision, with "in-the-wild" environments such as human-computer interaction. However, FER images contain uncertainties such as occlusion, low resolution,…
Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose…
Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces…
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is…
Single-image super-resolution (SISR) has seen significant advancements through the integration of deep learning. However, the substantial computational and memory requirements of existing methods often limit their practical application.…
Multitemporal hyperspectral image unmixing (MTHU) holds significant importance in monitoring and analyzing the dynamic changes of surface. However, compared to single-temporal unmixing, the multitemporal approach demands comprehensive…
In this paper, we tackle the high computational overhead of Transformers for efficient image super-resolution~(SR). Motivated by the observations of self-attention's inter-layer repetition, we introduce a convolutionized self-attention…
Eye movement (EM) is a new highly secure biometric behavioral modality that has received increasing attention in recent years. Although deep neural networks, such as convolutional neural network (CNN), have recently achieved promising…
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…