Related papers: HTMA-Net: Towards Multiplication-Avoiding Neural N…

While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various…

The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition…

Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where…

Diffusion models have demonstrated significant applications in the field of image generation. However, their high computational and memory costs pose challenges for deployment. Model quantization has emerged as a promising solution to…

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Recently, deep learning methods have been widely used for tumor segmentation of multimodal medical images with promising results. However, most existing methods are limited by insufficient representational ability, specific modality number…

Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great success by either following the alignment and fusion pipeline…

Constrained by the low-rank bottleneck inherent in attention mechanisms, current stereo matching transformers suffer from limited nonlinear expressivity, which renders their feature representations sensitive to challenging conditions such…

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and…

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and…

The classical approach of avoiding or ignoring interference in wireless networks cannot accommodate the ambitious quality-of-service demands of ultra-dense cellular networks (CNs). However, recent ground-breaking information-theoretic…

Tomographic synthetic aperture radar (TomoSAR) imaging algorithms based on deep learning can effectively reduce computational costs. The idea of existing researches is to reconstruct the elevation for each range-azimuth cell in…

Complicated image registration is a key issue in medical image analysis, and deep learning-based methods have achieved better results than traditional methods. The methods include ConvNet-based and Transformer-based methods. Although…

Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications. To tackle this limitation,…

Polynomial multiplication is one of the fundamental operations in many applications, such as fully homomorphic encryption (FHE). However, the computational inefficiency stemming from polynomials with many large-bit coefficients poses a…

Recent advancements in medical imaging have resulted in more complex and diverse images, with challenges such as high anatomical variability, blurred tissue boundaries, low organ contrast, and noise. Traditional segmentation methods…

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

The dense output projection in multi head attention scales quadratically with model dimension, contributing significantly to parameter count, memory footprint, and inference cost. We propose replacing this projection with a fixed, parameter…

Continual learning is a desirable feature in many modern machine learning applications, which allows in-field adaptation and updating, ranging from accommodating distribution shift, to fine-tuning, and to learning new tasks. For…