Improving Fast Segmentation With Teacher-student Learning

Abstract

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their application scenarios in practice. Meanwhile, existing fast segmentation models usually fail to obtain satisfactory segmentation accuracies on public benchmarks. In this paper, we propose a teacher-student learning framework that transfers the knowledge gained by a heavy and better performed segmentation network (i.e. teacher) to guide the learning of fast segmentation networks (i.e. student). Specifically, both zero-order and first-order knowledge depicted in the fine annotated images and unlabeled auxiliary data are transferred to regularize our student learning. The proposed method can improve existing fast segmentation models without incurring extra computational overhead, so it can still process images with the same fast speed. Extensive experiments on the Pascal Context, Cityscape and VOC 2012 datasets demonstrate that the proposed teacher-student learning framework is able to significantly boost the performance of student network.

arXiv comment13 pages, 3 figures, conference

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Residual Learning for Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• FitNets: Hints for Thin Deep Nets
• Multi-Scale Context Aggregation by Dilated Convolutions
• ParseNet: Looking Wider to See Better
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Pyramid Scene Parsing Network
• Simultaneous Detection and Segmentation
• ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Cited by in corpus (15)

• Efficient Medical Image Segmentation Based on Knowledge Distillation
• Double Similarity Distillation for Semantic Image Segmentation
• Structured Consistency Loss for semi-supervised semantic segmentation
• Structured Knowledge Distillation for Dense Prediction
• MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets
• Data Efficient Stagewise Knowledge Distillation
• Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
• Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network
• Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
• Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data
• Data-free Knowledge Distillation for Segmentation using Data-Enriching GAN
• MobileFAN: Transferring Deep Hidden Representation for Face Alignment
• Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer
• WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation