Related papers: Multi-scale Attention Network for Single Image Sup…
Although deep convolutional neural networks (CNNs) have obtained outstanding performance in image superresolution (SR), their computational cost increases geometrically as CNN models get deeper and wider. Meanwhile, the features of…
Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost.…
Attention mechanisms have been widely applied in the Visual Question Answering (VQA) task, as they help to focus on the area-of-interest of both visual and textual information. To answer the questions correctly, the model needs to…
Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using…
General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution face images. Recent deep learning based methods tailored for face images have achieved improved performance…
Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce this cost to…
The rapid development of spatial transcriptomics (ST) offers new opportunities to explore the gene expression patterns within the spatial microenvironment. Current research integrates pathological images to infer gene expression, addressing…
Deep learning typically relies on end-to-end backpropagation for training, a method that inherently suffers from issues such as update locking during parameter optimization, high GPU memory consumption, and a lack of biological…
Medical image segmentation plays an important role in various clinical applications; however, existing deep learning models face trade-offs between efficiency and accuracy. Convolutional Neural Networks (CNNs) capture local details well but…
By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic interaction within deep neural networks (DNNs) reveals the…
Multi-image super-resolution, which aims to fuse and restore a high-resolution image from multiple images at the same location, is crucial for utilizing satellite images. The satellite images are often occluded by atmospheric disturbances…
Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution…
Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…
While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…
Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…
The task of crowd counting in varying density scenes is an extremely difficult challenge due to large scale variations. In this paper, we propose a novel dual path multi-scale fusion network architecture with attention mechanism named…
As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation…
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…
There is a growing amount of literature on the relationship between wide neural networks (NNs) and Gaussian processes (GPs), identifying an equivalence between the two for a variety of NN architectures. This equivalence enables, for…