MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling

TL;DR

This paper introduces a multi-level self-supervised learning approach for domain adaptation in semantic segmentation, generating spatially independent pseudo-labels and leveraging global context to improve performance across different datasets.

Contribution

It proposes a novel multi-level self-supervised framework that creates spatially independent and semantically consistent pseudo-labels for better domain adaptation.

Findings

Achieves a 5.1% mIoU improvement on GTA-V to Cityscapes adaptation.

Achieves a 4.3% mIoU improvement on SYNTHIA to Cityscapes adaptation.

Outperforms existing state-of-the-art methods in domain adaptation for semantic segmentation.

Abstract

Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to limited training data and large distribution gap in train and test domain datasets. In this paper, we propose a multi-level self-supervised learning model for domain adaptation of semantic segmentation. Exploiting the idea that an object (and most of the stuff given context) should be labeled consistently regardless of its location, we generate spatially independent and semantically consistent (SISC) pseudo-labels by segmenting multiple sub-images using base model and designing an aggregation strategy. Image level pseudo weak-labels, PWL, are computed to guide domain adaptation by capturing global context similarity in source and domain at latent space level. Thus helping latent space learn the representation even when there are very few pixels belonging to the domain category (small object for example) compared to rest of the image. Our multi-level Self-supervised learning (MLSL) outperforms existing state-of art (self or adversarial learning) algorithms. Specifically, keeping all setting similar and employing MLSL we obtain an mIoU gain of 5:1% on GTA-V to Cityscapes adaptation and 4:3% on SYNTHIA to Cityscapes adaptation compared to existing state-of-art method.