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

Code

• github.com/james128333/HarDNet-MSEG
  OfficialIn paperpytorch★ 136
• github.com/lanPN85/HarDNet-MSEG
  pytorch★ 1
• github.com/sahadevpoudel/hardnet-mseg
  pytorch★ 0
• github.com/2023-MindSpore-4/Code10/tree/main/hardnet
  mindspore★ 0

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

Tasks

Benchmark Results

Reproductions