Related papers: PGKET: A Photonic Gaussian Kernel Enhanced Transfo…

Parameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters. Compared to traditional fine-tuning, which updates the entire model, PET significantly reduces…

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…

Transformer has been very successful in various computer vision tasks and understanding the working mechanism of transformer is important. As touchstones, weakly-supervised semantic segmentation (WSSS) and class activation map (CAM) are…

Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably,…

The Segment Anything Model (SAM) is widely used for segmenting a diverse range of objects in natural images from simple user prompts like points or bounding boxes. However, SAM's performance decreases substantially when applied to…

Accurate lesion segmentation in whole-body PET/CT scans is crucial for cancer diagnosis and treatment planning, but limited datasets often hinder the performance of automated segmentation models. In this paper, we explore the potential of…

Humans can effectively find salient regions in complex scenes. Self-attention mechanisms were introduced into Computer Vision (CV) to achieve this. Attention Augmented Convolutional Network (AANet) is a mixture of convolution and…

Computed tomography (CT) uses X-ray measurements taken from sensors around the body to generate tomographic images of the human body. Conventional reconstruction algorithms can be used if the X-ray data are adequately sampled and of high…

The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs)…

With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain. However, the massive computation brought from the full attention mechanism became a…

We introduce photonic kernel machines, a scheme for ultrafast spectral analysis of noisy radio-frequency signals from single-shot optical intensity measurements. The approach combines the versatility of machine learning and the speed of…

Single image super-resolution is a well-known downstream task which aims to restore low-resolution images into high-resolution images. At present, models based on Transformers have shone brightly in the field of super-resolution due to…

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to…

Predicting the effect of amino acid mutations on enzyme thermodynamic stability (DDG) is fundamental to protein engineering and drug design. While recent deep learning approaches have shown promise, they often process sequence and structure…

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…

FDG PET/CT imaging is a resource intensive examination critical for managing malignant disease and is particularly important for longitudinal assessment during therapy. Approaches to automate longtudinal analysis present many challenges…

Despite the remarkable empirical performance of Transformers, their theoretical understanding remains elusive. Here, we consider a deep multi-head self-attention network, that is closely related to Transformers yet analytically tractable.…

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Acquiring labels are often costly, whereas unlabeled data are usually easy to obtain in modern machine learning applications. Semi-supervised learning provides a principled machine learning framework to address such situations, and has been…

Arterial blood pressure (ABP) holds substantial promise for proactive cardiovascular health management. Notwithstanding its potential, the invasive nature of ABP measurements confines their utility primarily to clinical environments,…