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

arXiv: https://arxiv.org/abs/1909.13776 · HTML: https://mlsanity.com/paper/1909.13776/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training](https://mlsanity.com/paper/2105.08128/) (2021)
- [MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2103.05254/) (2021)
- [Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07830/) (2021)
- [Domain Adaptive Semantic Segmentation without Source Data](https://mlsanity.com/paper/2110.06484/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation](https://mlsanity.com/paper/2304.13615/) (2023)
- [SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.15202/) (2022)
- [UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration](https://mlsanity.com/paper/2206.15083/) (2022)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2302.06992/) (2023)
- [Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2212.04227/) (2022)
- [One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers](https://mlsanity.com/paper/2212.07292/) (2022)
- [Cross-Region Building Counting in Satellite Imagery using Counting Consistency](https://mlsanity.com/paper/2110.13558/) (2021)
- [Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2206.09683/) (2022)
- [Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation](https://mlsanity.com/paper/2204.06747/) (2022)
- [Leveraging Topology for Domain Adaptive Road Segmentation in Satellite and Aerial Imagery](https://mlsanity.com/paper/2309.15625/) (2023)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)
- [Domain Adaptive Semantic Segmentation by Optimal Transport](https://mlsanity.com/paper/2303.16435/) (2023)

## Abstract (arXiv)

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.