Related papers: NOVA: NoC-based Vector Unit for Mapping Attention …

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to…

In the task of emotion recognition from videos, a key improvement has been to focus on emotions over time rather than a single frame. There are many architectures to address this task such as GRUs, LSTMs, Self-Attention, Transformers, and…

This project provides a comparative study of dynamic convolutional neural networks (CNNs) for various tasks, including image classification, segmentation, and time series analysis. Based on the ResNet-18 architecture, we compare five…

Sequential recommender systems aim to model users' evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN…

Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function…

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

The attention mechanism is the primary component of the transformer architecture; it has led to significant advancements in deep learning spanning many domains and covering multiple tasks. In computer vision, the attention mechanism was…

This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects. First, ACNet employs a flexible way to switch global and local inference in processing…

Network-on-Chip (NoC) plays a significant role in the performance of a DNN accelerator. The scalability and modular design property of the NoC help in improving the performance of a DNN execution by providing flexibility in running…

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…

The increasing application of deep learning technology drives the need for an efficient parallel computing architecture for Convolutional Neural Networks (CNNs). A significant challenge faced when designing a many-core CNN accelerator is to…

We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global…

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt…

Line detection is a basic digital image processing operation used by higher-level processing methods. Recently, transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of…

Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three…

In radiotherapy planning, manual contouring is labor-intensive and time-consuming. Accurate and robust automated segmentation models improve the efficiency and treatment outcome. We aim to develop a novel hybrid deep learning approach,…

Resistive Random-Access Memory (RRAM) is well-suited to accelerate neural network (NN) workloads as RRAM-based Processing-in-Memory (PIM) architectures natively support highly-parallel multiply-accumulate (MAC) operations that form the…

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead,…

Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and…

Recently, attention-based Visual Question Answering (VQA) has achieved great success by utilizing question to selectively target different visual areas that are related to the answer. Existing visual attention models are generally planar,…