Mask-based Data Augmentation for Semi-supervised Semantic Segmentation

TL;DR

This paper introduces ComplexMix, a novel data augmentation technique for semi-supervised semantic segmentation that improves performance by controlling augmentation complexity and semantic correctness.

Contribution

The paper proposes ComplexMix, a new data augmentation method that combines aspects of CutMix and ClassMix with enhanced control over augmentation complexity.

Findings

ComplexMix outperforms state-of-the-art augmentation methods on standard datasets.

The approach effectively balances augmentation complexity and semantic correctness.

Experimental results demonstrate improved segmentation accuracy.

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.