Two-Stage Framework for Faster Semantic Segmentation
Open Access
Abstract
Semantic segmentation consists of classifying each pixel according to a set of classes. Conventional models spend as much effort classifying easy-to-segment pixels as they do classifying hard-to-segment pixels. This is inefficient, especially when deploying to situations with computational constraints. In this work, we propose a framework wherein the model first produces a rough segmentation of the image, and then patches of the image estimated as hard to segment are refined. The framework is evaluated in four datasets (autonomous driving and biomedical), across four state-of-the-art architectures. Our method accelerates inference time by four, with additional gains for training time, at the cost of some output quality.Keywords
Funding Information
- European Structural and Investment (POCI-01-0247-FEDER-047264, 2020.06434.BD)
- Portuguese funding agency (POCI-01-0247-FEDER-047264, 2020.06434.BD)
This publication has 16 references indexed in Scilit:
- Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving ScenesInternational Journal of Computer Vision, 2018
- Focal Loss for Dense Object Detection2017
- Iterative deep convolutional encoder-decoder network for medical image segmentation2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- PH2 - A dermoscopic image database for research and benchmarking2013
- Torchvision the machine-vision package of torch2010