# HarDNet: A Low Memory Traffic Network

arXiv: https://arxiv.org/abs/1909.00948 · HTML: https://mlsanity.com/paper/1909.00948/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 30 of 76)

- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS](https://mlsanity.com/paper/2101.07172/) (2021)
- [AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder](https://mlsanity.com/paper/2306.06370/) (2023)
- [NeoUNet: Towards accurate colon polyp segmentation and neoplasm detection](https://mlsanity.com/paper/2107.05023/) (2021)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition](https://mlsanity.com/paper/2207.02606/) (2022)
- [Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions](https://mlsanity.com/paper/2103.08852/) (2021)
- [PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation](https://mlsanity.com/paper/2101.06175/) (2021)
- [RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer](https://mlsanity.com/paper/2210.07124/) (2022)
- [Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World](https://mlsanity.com/paper/2107.03172/) (2021)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance](https://mlsanity.com/paper/2108.09174/) (2021)
- [Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy](https://mlsanity.com/paper/2105.07467/) (2021)
- [CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters](https://mlsanity.com/paper/2203.15331/) (2022)
- [Visual Representation Learning for Preference-Aware Path Planning](https://mlsanity.com/paper/2109.08968/) (2021)
- [Multi-domain semantic segmentation with overlapping labels](https://mlsanity.com/paper/2108.11224/) (2021)
- [Lightweight Monocular Depth Estimation through Guided Decoding](https://mlsanity.com/paper/2203.04206/) (2022)
- [Segmenting Transparent Object in the Wild with Transformer](https://mlsanity.com/paper/2101.08461/) (2021)
- [A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey](https://mlsanity.com/paper/2208.10895/) (2022)
- [Rethinking Dilated Convolution for Real-time Semantic Segmentation](https://mlsanity.com/paper/2111.09957/) (2021)
- [What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs](https://mlsanity.com/paper/2206.09358/) (2022)
- [BlazeNeo: Blazing fast polyp segmentation and neoplasm detection](https://mlsanity.com/paper/2203.00129/) (2022)
- [Recent Progress in Transformer-based Medical Image Analysis](https://mlsanity.com/paper/2208.06643/) (2022)
- [Panoptic Segmentation Forecasting](https://mlsanity.com/paper/2104.03962/) (2021)
- [Semantic Scene Segmentation for Robotics Applications](https://mlsanity.com/paper/2108.11128/) (2021)
- [Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability](https://mlsanity.com/paper/2207.12939/) (2022)
- [YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems](https://mlsanity.com/paper/2408.09332/) (2024)

## Abstract (arXiv)

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.