Papers › Adaptively Connected Neural Networks

Adaptively Connected Neural Networks

7 Apr 2019CVPR 2019 6arXiv:1904.03579archive 2025-07-28

Guangrun Wang, Keze Wang, Liang Lin

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{https://github.com/wanggrun/Adaptively-Connected-Neural-Networks}.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wanggrun/Adaptively-Connected-Neural-Networks officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document Classification Image Classification Person Re-Identification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Document Classification	Cora	ACNet	Accuracy	83.5%	#1 of 6	Archive leaderboard	report
Image Classification	ImageNet	ACNet (ResNet-50)	Number of params	29.38M	#873 of 1060	Archive leaderboard	report
Image Classification	ImageNet	ACNet (ResNet-50)	Top 1 Accuracy	77.5%	#873 of 1060	Archive leaderboard	report
Instance Segmentation	COCO minival	Mask R-CNN (ResNet-50, ACNet)	mask AP	35.2	#91 of 93	Archive leaderboard	report
Object Detection	COCO minival	Mask R-CNN (ResNet-50, ACNet)	box AP	39.5	#188 of 220	Archive leaderboard	report
Person Re-Identification	CUHK03	TriNet + Era + Reranking (ACNet, bs=32)	Rank-1	64.8	#19 of 19	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections