HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS

2021/01/18 by Chien‐Hsiang Huang, Huang, Chien-Hsiang, Hung-Yu Wu +3 · 7 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Vehicle License Plate Recognition

paper · pdf · doi:10.48550/arxiv.2101.07172

openalex publication_date 2021/01/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. It achieves SOTA in both accuracy and inference speed on five popular datasets. For Kvasir-SEG, HarDNet-MSEG delivers 0.904 mean Dice running at 86.7 FPS on a GeForce RTX 2080 Ti GPU. It consists of a backbone and a decoder. The backbone is a low memory traffic CNN called HarDNet68, which has been successfully applied to various CV tasks including image classification, object detection, multi-object tracking and semantic segmentation, etc. The decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection. We have evaluated HarDNet-MSEG using those five popular datasets. The code and all experiment details are available at Github. https://github.com/james128333/HarDNet-MSEG

Citations

• Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information

Cited by

• QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
• PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
• Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration
• The Role of Radiographic Knee Alignment in Total Knee Replacement Outcomes and Opportunities for Artificial Intelligence-Driven Assessment
• Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation
• The Power of Certainty: How Confident Models Lead to Better Segmentation
• CL-Polyp: A Contrastive Learning-Enhanced Network for Accurate Polyp Segmentation

Related

• BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp Segmentation
• PolypNextLSTM: a lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM
• PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM
• BlazeNeo: Blazing fast polyp segmentation and neoplasm detection
• RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget