A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation

Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by the success of semi-supervised learning methods in image classification, here we propose a simple yet effective semi-supervised learning framework for semantic segmentation. We demonstrate that the devil is in the details: a set of simple design and training techniques can collectively improve the performance of semi-supervised semantic segmentation significantly. Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics. We design a new batch normalisation, namely distribution-specific batch normalisation (DSBN) to address this problem and demonstrate the importance of strong augmentation for semantic segmentation. Moreover, we design a self correction loss which is effective in noise resistance. We conduct a series of ablation studies to show the effectiveness of each component. Our method achieves state-of-the-art results in the semi-supervised settings on the Cityscapes and Pascal VOC datasets.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled SimpleBaseline(DeeplabV3+ with ImageNet pretrained Xception65, sinle scale inference) Validation mIoU 74.1% # 13
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled SimpleBaseline(DeepLabv3+ with ImageNet pretrained Xception65, single scale inference) Validation mIoU 77.8% # 12
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled SimpleBaseline(DeepLabv3+ with ImageNet pretrained Xception65, single scale inference) Validation mIoU 78.7% # 12

Methods


No methods listed for this paper. Add relevant methods here