Adaptively Connected Neural Networks
share
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) [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) 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 [Corresponding author: Liang Lin (linliang@ieee.org)]. The code is available at <https://github.com/wanggrun/Adaptively-Connected-Neural-Networks>.
READ FULL TEXT
