# HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

arXiv: https://arxiv.org/abs/2403.16788 · HTML: https://mlsanity.com/paper/2403.16788/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 29 of 29)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [Hierarchical Multi-Scale Attention for Semantic Segmentation](https://mlsanity.com/paper/2005.10821/) (2020)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2011.09230/) (2020)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)
- [SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.08808/) (2022)
- [Exploiting Domain-Specific Features to Enhance Domain Generalization](https://mlsanity.com/paper/2110.09410/) (2021)
- [DDD17: End-To-End DAVIS Driving Dataset](https://mlsanity.com/paper/1711.01458/) (2017)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [Event-based, 6-DOF Camera Tracking from Photometric Depth Maps](https://mlsanity.com/paper/1607.03468/) (2016)
- [HFirst: A Temporal Approach to Object Recognition](https://mlsanity.com/paper/1508.01176/) (2015)
- [EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation](https://mlsanity.com/paper/2111.12341/) (2021)
- [Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.02618/) (2021)
- [Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation](https://mlsanity.com/paper/2109.01801/) (2021)
- [Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond](https://mlsanity.com/paper/2204.08200/) (2022)
- [Semi-Supervised Domain Adaptation with Source Label Adaptation](https://mlsanity.com/paper/2302.02335/) (2023)
- [HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities](https://mlsanity.com/paper/2211.10754/) (2022)
- [X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer](https://mlsanity.com/paper/2312.07378/) (2023)

## Built on by (most cited first, 9 of 9)

- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [EventFly: Event Camera Perception from Ground to the Sky](https://mlsanity.com/paper/2503.19916/) (2025)
- [Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras](https://mlsanity.com/paper/2507.17664/) (2025)
- [EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation](https://mlsanity.com/paper/2603.09385/) (2026)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Learning to Remove Lens Flare in Event Camera](https://mlsanity.com/paper/2512.09016/) (2025)
- [Scaling Dense Event-Stream Pretraining from Visual Foundation Models](https://mlsanity.com/paper/2603.03969/) (2026)
- [EventDrive: Event Cameras for Vision-Language Driving Intelligence](https://mlsanity.com/paper/2606.18242/) (2026)
- [Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation](https://mlsanity.com/paper/2511.08269/) (2025)

## Abstract (arXiv)

Event-based semantic segmentation has gained popularity due to its capability to deal with scenarios under high-speed motion and extreme lighting conditions, which cannot be addressed by conventional RGB cameras. Since it is hard to annotate event data, previous approaches rely on event-to-image reconstruction to obtain pseudo labels for training. However, this will inevitably introduce noise, and learning from noisy pseudo labels, especially when generated from a single source, may reinforce the errors. This drawback is also called confirmation bias in pseudo-labeling. In this paper, we propose a novel hybrid pseudo-labeling framework for unsupervised event-based semantic segmentation, HPL-ESS, to alleviate the influence of noisy pseudo labels. In particular, we first employ a plain unsupervised domain adaptation framework as our baseline, which can generate a set of pseudo labels through self-training. Then, we incorporate offline event-to-image reconstruction into the framework, and obtain another set of pseudo labels by predicting segmentation maps on the reconstructed images. A noisy label learning strategy is designed to mix the two sets of pseudo labels and enhance the quality. Moreover, we propose a soft prototypical alignment module to further improve the consistency of target domain features. Extensive experiments show that our proposed method outperforms existing state-of-the-art methods by a large margin on the DSEC-Semantic dataset (+5.88% accuracy, +10.32% mIoU), which even surpasses several supervised methods.