# Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation

arXiv: https://arxiv.org/abs/2303.14361 · HTML: https://mlsanity.com/paper/2303.14361/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 55 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation](https://mlsanity.com/paper/1903.12212/) (2019)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training](https://mlsanity.com/paper/2105.08128/) (2021)
- [Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video](https://mlsanity.com/paper/1807.06667/) (2018)
- [Temporally Distributed Networks for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2004.01800/) (2020)

## Built on by (most cited first, 10 of 10)

- [Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2407.10299/) (2024)
- [Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer](https://mlsanity.com/paper/2303.17783/) (2023)
- [Unsupervised Camouflaged Object Segmentation as Domain Adaptation](https://mlsanity.com/paper/2308.04528/) (2023)
- [We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline](https://mlsanity.com/paper/2402.00868/) (2024)
- [Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation](https://mlsanity.com/paper/2604.10950/) (2026)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [Adaptive Batch Normalization Networks for Adversarial Robustness](https://mlsanity.com/paper/2405.11708/) (2024)
- [PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning](https://mlsanity.com/paper/2407.17101/) (2024)
- [MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding](https://mlsanity.com/paper/2507.06072/) (2025)
- [AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images](https://mlsanity.com/paper/2503.03370/) (2025)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data. However, the access to source data is often restricted or infeasible in real-world scenarios. Under the source data restrictive circumstances, UDA is less practical. To address this, recent works have explored solutions under the Source-Free Domain Adaptation (SFDA) setup, which aims to adapt a source-trained model to the target domain without accessing source data. Still, existing SFDA approaches use only image-level information for adaptation, making them sub-optimal in video applications. This paper studies SFDA for Video Semantic Segmentation (VSS), where temporal information is leveraged to address video adaptation. Specifically, we propose Spatio-Temporal Pixel-Level (STPL) contrastive learning, a novel method that takes full advantage of spatio-temporal information to tackle the absence of source data better. STPL explicitly learns semantic correlations among pixels in the spatio-temporal space, providing strong self-supervision for adaptation to the unlabeled target domain. Extensive experiments show that STPL achieves state-of-the-art performance on VSS benchmarks compared to current UDA and SFDA approaches. Code is available at: https://github.com/shaoyuanlo/STPL