Related papers: RepGhost: A Hardware-Efficient Ghost Module via Re…

Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization. Unfortunately, to preserve the statistical…

Convolutional Neural Networks (CNNs) have proven highly effective for edge and mobile vision tasks due to their computational efficiency. While many recent works seek to enhance CNNs with global contextual understanding via…

Deep residual networks have recently emerged as the state-of-the-art architecture in image segmentation and object detection. In this paper, we propose new image features (called ResFeats) extracted from the last convolutional layer of deep…

Fixed-point quantization and binarization are two reduction methods adopted to deploy Convolutional Neural Networks (CNN) on end-nodes powered by low-power micro-controller units (MCUs). While most of the existing works use them as…

Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining high model capacity. However, in memory-constrained inference scenarios, only a small set of…

Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…

While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV)…

In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concatenated attention neural network (CANet) is specifically…

As the complexity of deep neural networks (DNNs) trend to grow to absorb the increasing sizes of data, memory and energy consumption has been receiving more and more attentions for industrial applications, especially on mobile devices. This…

Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…

We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…

There is a growing interest in portable MRI (pMRI) systems for point-of-care imaging, particularly in remote or resource-constrained environments. However, the computational complexity of pMRI, especially in image reconstruction and machine…

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding…

Neural materials typically consist of a collection of neural features along with a decoder network. The main challenge in integrating such models in real-time rendering pipelines lies in the large size required to store their features in…

Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-task models are often overlooked in literature. First,…

We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional…

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…

Masked image modeling has achieved great success in learning representations but is limited by the huge computational costs. One cost-saving strategy makes the decoder reconstruct only a subset of masked tokens and throw the others, and we…

Masked generative models (MGMs) have emerged as a powerful framework for image synthesis, combining parallel decoding with strong bidirectional context modeling. However, generating high-quality samples typically requires many iterative…

TBecause of limited energy of nodes, an important issue for sensor network is efficient use of the energy. The clustering technique reduces energy consumption as cluster head sends sensed information to a sink node. Because of such…