Paper Reading AI Learner

Adaptively Connected Neural Networks

2019-04-07 04:01:27
Guangrun Wang, Keze Wang, Liang Lin

Abstract

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 the internal feature representations by adaptively determining the connection status among the feature nodes (e.g., pixels of the feature maps) \footnote{In a computer vision domain, a node refers to a pixel of a feature map{, while} in {the} graph domain, a node denotes a graph node.}. We can show that existing CNNs, the classical multilayer perceptron (MLP), and the recently proposed non-local network (NLN) \cite{nonlocalnn17} are all special cases of ACNet. Second, ACNet is also capable of handling non-Euclidean data. Extensive experimental analyses on {a variety of benchmarks (i.e.,} ImageNet-1k classification, COCO 2017 detection and segmentation, CUHK03 person re-identification, CIFAR analysis, and Cora document categorization) demonstrate that {ACNet} cannot only achieve state-of-the-art performance but also overcome the limitation of the conventional MLP and CNN \footnote{Corresponding author: Liang Lin (linliang@ieee.org)}. The code is available at \url{this https URL}.

Abstract (translated)

本文提出了一种新的自适应连接神经网络(ACNET),从两个方面对传统的卷积神经网络(CNN)进行了改进。首先,ACNET采用灵活的方式切换全局和局部推理处理内部特征表示,通过自适应地确定特征节点之间的连接状态(例如,特征映射的像素)footnote在计算机视觉域中,节点指的是特征映射的像素,而在图形域中,节点指的是特征映射的像素。e表示图形节点。我们可以证明,现有的CNN、经典的多层感知器(MLP)和最近提出的非局域网络(NLN)都是ACNET的特例。其次,acnet还能够处理非欧几里得数据。对各种基准(即IMAGENET-1K分类、COCO 2017检测与分割、CUHK03人员重新识别、CIFAR分析和CORA文件分类)进行了广泛的实验分析,证明ACNET不仅能达到最先进的性能,而且克服了传统MLP A的局限性。ND CNN 脚注通讯作者:梁林(lin liang@ieee.org)。此代码位于url此https url。

URL

https://arxiv.org/abs/1904.03579

PDF

https://arxiv.org/pdf/1904.03579.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot