Adaptively Connected Neural Networks

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.}... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 Standard ACNet Percentage correct 94 # 95
Object Detection COCO minival Mask R-CNN (ResNet-50, ACNet) box AP 39.5 # 87
Instance Segmentation COCO minival Mask R-CNN (ResNet-50, ACNet) mask AP 35.2 # 37
Document Classification Cora ACNet Accuracy 83.5% # 1
Person Re-Identification CUHK03 TriNet + Era + Reranking (ACNet, bs=32) Rank-1 64.8 # 8
Image Classification ImageNet ACNet (ResNet-50) Top 1 Accuracy 77.5% # 271
Number of params 29.38M # 121

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks