Adaptively Connected Neural Networks

By Guangrun Wang, Keze Wang, Liang Lin. 2019

55 citations recorded by the source corpus.

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). Note that 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) 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. The code is available at https://github.com/wanggrun/Adaptively-Connected-Neural-Networks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shiji Song
2. Ziwei Liu
3. Chen Change Loy
4. Yulin Wang
5. Gao Huang
6. Songtao Liu
7. Le Yang
8. Yizeng Han

In Computer Vision and Pattern Recognition

1. Chen Change Loy
2. Shiji Song
3. Ziwei Liu
4. Luc Van Gool
5. Gao Huang
6. Xiaogang Wang
7. Songtao Liu
8. Yunhong Wang

In Model Architectures

1. Chen Change Loy
2. Shiji Song
3. Ziwei Liu
4. Yulin Wang
5. Gao Huang
6. Yunhong Wang
7. Honghui Wang
8. Zhaoxi Chen

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “Others Time series forecasting [248], [249], [250], Link prediction [251], Recommendation system [77], [252], [253], [254] Graph classification [121], Document classification [156], [255], [256], [257], Stereo confidence estimation [258]”
• SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis (2023, background): “NeRF [36, 48, 8, 39] has made great success in synthesizing novel views of complex scenes due to good representation of neural networks [20, 52, 50, 53, 18, 28].”
• Learning Spatial Fusion for Single-Shot Object Detection (2019, methodology): “Inspired by [37], we force and define Here α , β and γ lij are defined by using the softmax function with λ ij , λ lβ ij and λ lγ ij as control parameters respectively.”