相关论文: TENT: Efficient Quantization of Neural Networks on…

While neural networks have advanced the frontiers in many machine learning applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is vital to integrating modern networks into…

As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…

Advanced tensor decomposition, such as Tensor train (TT) and Tensor ring (TR), has been widely studied for deep neural network (DNN) model compression, especially for recurrent neural networks (RNNs). However, compressing convolutional…

In this work we propose a novel attention-based neural network model for the task of fine-grained entity type classification that unlike previously proposed models recursively composes representations of entity mention contexts. Our model…

Deep neural networks (DNNs) have been demonstrated as effective prognostic models across various domains, e.g. natural language processing, computer vision, and genomics. However, modern-day DNNs demand high compute and memory storage for…

Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an…

Within the domain of medical image analysis, three distinct methodologies have demonstrated commendable accuracy: Neural Networks, Decision Trees, and Ensemble-Based Learning Algorithms, particularly in the specialized context of genstro…

Modern CNN are typically based on floating point linear algebra based implementations. Recently, reduced precision NN have been gaining popularity as they require significantly less memory and computational resources compared to floating…

This paper presents Segment This Thing (STT), a new efficient image segmentation model designed to produce a single segment given a single point prompt. Instead of following prior work and increasing efficiency by decreasing model size, we…

While post-training model compression can greatly reduce the inference cost of a deep neural network, uncompressed training still consumes a huge amount of hardware resources, run-time and energy. It is highly desirable to directly train a…

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

3D point cloud has been widely used in many mobile application scenarios, including autonomous driving and 3D sensing on mobile devices. However, existing 3D point cloud models tend to be large and cumbersome, making them hard to deploy on…

Packet classification is a core function in software-defined networks, and learning-based methods have recently shown significant throughput gains on large-scale rulesets. However, existing learning-based approaches struggle with…

In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in…

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their…

This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a…

Due to the complicated background and noise of infrared images, infrared small target detection is one of the most difficult problems in the field of computer vision. In most existing studies, semantic segmentation methods are typically…

We introduce an Artificial Neural Network (ANN) quantization methodology for platforms without wide accumulation registers. This enables fixed-point model deployment on embedded compute platforms that are not specifically designed for large…

This paper presents a compact model architecture called MOGNET, compatible with a resource-limited hardware. MOGNET uses a streamlined Convolutional factorization block based on a combination of 2 point-wise (1x1) convolutions with a…

ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth…