Papers › HarDNet: A Low Memory Traffic Network

HarDNet: A Low Memory Traffic Network

3 Sep 2019ICCV 2019 10arXiv:1909.00948archive 2025-07-28

Ping Chao, Chao-Yang Kao, Yu-Shan Ruan, Chien-Hsiang Huang, Youn-Long Lin

State-of-the-art neural network architectures such as ResNet, MobileNet, and DenseNet have achieved outstanding accuracy over low MACs and small model size counterparts. However, these metrics might not be accurate for predicting the inference time. We suggest that memory traffic for accessing intermediate feature maps can be a factor dominating the inference latency, especially in such tasks as real-time object detection and semantic segmentation of high-resolution video. We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic. The new network achieves 35%, 36%, 30%, 32%, and 45% inference time reduction compared with FC-DenseNet-103, DenseNet-264, ResNet-50, ResNet-152, and SSD-VGG, respectively. We use tools including Nvidia profiler and ARM Scale-Sim to measure the memory traffic and verify that the inference latency is indeed proportional to the memory traffic consumption and the proposed network consumes low memory traffic. We conclude that one should take memory traffic into consideration when designing neural network architectures for high-resolution applications at the edge.

PaperPDFConference PDFCode

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

Code

24 repositories listed; official and paper-mentioned ones first.

PingoLH/Pytorch-HarDNet officialmentioned on GitHubpytorch report
GibranBenitez/IPN-hand mentioned on GitHubpytorch report
Mind23-2/MindCode-51 mentioned on GitHubmindspore report
PingoLH/CenterNet-HarDNet mentioned on GitHubpytorchMIT report
PingoLH/FCHarDNet mentioned on GitHubpytorch report
coreqode/HardNet mentioned on GitHubtf report
james128333/HarDNet-MSEG mentioned on GitHubpytorch report
lanPN85/HarDNet-MSEG mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
sahadevpoudel/hardnet-mseg mentioned on GitHubpytorch report
sithu31296/semantic-segmentation mentioned on GitHubpytorch report
talshaharabany/DeepACM2D mentioned on GitHubpytorch report
yktangac/CenterHarDNet mentioned on GitHubpytorch report
PaddlePaddle/PaddleClas paddleApache-2.0 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

Object DetectionReal-Time Object DetectionReal-Time Semantic SegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation Cityscapes test U-HarDNet-70 Frame (fps) 53 (1080Ti) #10 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test U-HarDNet-70 Time (ms) 18.8 (1080Ti) #10 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test U-HarDNet-70 mIoU 75.9% #10 of 39 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 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSoftmax

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