Related papers: SWIFT: A General Sensitive Weight Identification F…

Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge, which is critical for real-world applications. This paper…

Pansharpening, a pivotal task in remote sensing, involves integrating low-resolution multispectral images with high-resolution panchromatic images to synthesize an image that is both high-resolution and retains multispectral information.…

The implementation of diffusion-based pansharpening task is predominantly constrained by its slow inference speed, which results from numerous sampling steps. Despite the existing techniques aiming to accelerate sampling, they often…

Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics systems. However, state-of-the-art semantic segmentation pipelines are dominantly designed to work with pinhole cameras and train with narrow…

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale…

Recently, deep learning-based pan-sharpening algorithms have achieved notable advancements over traditional methods. However, deep learning-based methods incur substantial computational overhead during inference, especially with large…

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…

In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision. Most existing methods have addressed the challenges arising from the lack…

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely…

The Swin transformer has recently attracted attention in medical image analysis due to its computational efficiency and long-range modeling capability. Owing to these properties, the Swin Transformer is suitable for establishing more…

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

Recent salient object detection (SOD) models predominantly rely on heavyweight backbones, incurring substantial computational cost and hindering their practical application in various real-world settings, particularly on edge devices. This…

Semantic segmentation is a core task in computer vision with applications in biomedical imaging, remote sensing, and autonomous driving. While standard loss functions such as cross-entropy and Dice loss perform well in general cases, they…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

We consider simultaneous wireless information and power transfer (SWIPT) in MIMO Broadcast networks where one energy harvesting (EH) user and one information decoding (ID) user share the same time and frequency resource. In contrast to…

Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…

Transformers have achieved remarkable results in single-image super-resolution (SR). However, the challenge of balancing model performance and complexity has hindered their application in lightweight SR (LSR). To tackle this challenge, we…

Pretrained Foundation Models (PFMs) have transformed numerous applications by enabling efficient adaptation to customized tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient alternative to full fine-tuning,…

Deep learning models deployed in real-world applications (e.g., medicine) face challenges because source models do not generalize well to domain-shifted target data. Many successful domain adaptation (DA) approaches require full access to…