Training and Inference for Integer-Based Semantic Segmentation Network

by   Jiayi Yang, et al.

Semantic segmentation has been a major topic in research and industry in recent years. However, due to the computation complexity of pixel-wise prediction and backpropagation algorithm, semantic segmentation has been demanding in computation resources, resulting in slow training and inference speed and large storage space to store models. Existing schemes that speed up segmentation network change the network structure and come with noticeable accuracy degradation. However, neural network quantization can be used to reduce computation load while maintaining comparable accuracy and original network structure. Semantic segmentation networks are different from traditional deep convolutional neural networks (DCNNs) in many ways, and this topic has not been thoroughly explored in existing works. In this paper, we propose a new quantization framework for training and inference of segmentation networks, where parameters and operations are constrained to 8-bit integer-based values for the first time. Full quantization of the data flow and the removal of square and root operations in batch normalization give our framework the ability to perform inference on fixed-point devices. Our proposed framework is evaluated on mainstream semantic segmentation networks like FCN-VGG16 and DeepLabv3-ResNet50, achieving comparable accuracy against floating-point framework on ADE20K dataset and PASCAL VOC 2012 dataset.


page 11

page 14


Training Bit Fully Convolutional Network for Fast Semantic Segmentation

Fully convolutional neural networks give accurate, per-pixel prediction ...

Normalization in Training Deep Convolutional Neural Networks for 2D Bio-medical Semantic Segmentation

2D bio-medical semantic segmentation is important for surgical robotic v...

Accelerating Neural Network Inference by Overflow Aware Quantization

The inherent heavy computation of deep neural networks prevents their wi...

A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation

Confusing classes that are ubiquitous in real world often degrade perfor...

EdgeSegNet: A Compact Network for Semantic Segmentation

In this study, we introduce EdgeSegNet, a compact deep convolutional neu...

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

In this paper, we propose to train convolutional neural networks (CNNs) ...

Light-Weight RefineNet for Real-Time Semantic Segmentation

We consider an important task of effective and efficient semantic image ...

Please sign up or login with your details

Forgot password? Click here to reset