ComplexMix: Semi-Supervised Semantic Segmentation Via Mask-Based Data Augmentation
Authors:
- 19 September 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2264-2268
Abstract
Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive. Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. In particular, data augmentation techniques such as CutMix and ClassMix generate additional training data from existing labeled data. In this paper we propose a new approach for data augmentation, termed ComplexMix, which incorporates aspects of CutMix and ClassMix with improved performance. The proposed approach has the ability to control the complexity of the augmented data while attempting to be semantically-correct and address the tradeoff between complexity and correctness. The proposed ComplexMix approach is evaluated on a standard dataset for semantic segmentation and compared to other state-of-the-art techniques. Experimental results show that our method yields improvement over state-of-the-art methods on standard datasets for semantic image segmentation.Keywords
This publication has 8 references indexed in Scilit:
- Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation2020
- Semi-Supervised Semantic Segmentation With Cross-Consistency Training2020
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Interpolation Consistency Training for Semi-supervised Learning2019
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016