Related papers: SPFormer: Enhancing Vision Transformer with Superp…

Image deblurring continues to achieve impressive performance with the development of generative models. Nonetheless, there still remains a displeasing problem if one wants to improve perceptual quality and quantitative scores of recovered…

Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet…

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral…

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…

Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision…

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two…

Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for building low-power Transformers. However, existing Spiking Transformers largely adhere to a…

Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to…

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image…

Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort…

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce…

Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment.Driven by rapid…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Hyperspectral image segmentation is crucial for many fields such as agriculture, remote sensing, biomedical imaging, battlefield sensing and astronomy. However, the challenge of hyper and multi spectral imaging is its large data footprint.…

This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various levels of Gaussian…

The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently…

The accurate analysis of medical images is vital for diagnosing and predicting medical conditions. Traditional approaches relying on radiologists and clinicians suffer from inconsistencies and missed diagnoses. Computer-aided diagnosis…

Superpixels have long been used in image simplification to enable more efficient data processing and storage. However, despite their computational potential, their irregular spatial distribution has often forced deep learning approaches to…