# Knowledge Distillation for Semantic Segmentation: A Label Space Unification Approach

arXiv: https://arxiv.org/abs/2502.19177 · HTML: https://mlsanity.com/paper/2502.19177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [The ApolloScape Open Dataset for Autonomous Driving and its Application](https://mlsanity.com/paper/1803.06184/) (2018)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [RELLIS-3D Dataset: Data, Benchmarks and Analysis](https://mlsanity.com/paper/2011.12954/) (2020)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022)
- [Universal Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1811.10323/) (2018)
- [Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation](https://mlsanity.com/paper/2005.10266/) (2020)
- [The GOOSE Dataset for Perception in Unstructured Environments](https://mlsanity.com/paper/2310.16788/) (2023)
- [PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model](https://mlsanity.com/paper/2204.02681/) (2022)
- [Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2103.11351/) (2021)
- [Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation](https://mlsanity.com/paper/1803.05675/) (2018)
- [A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios](https://mlsanity.com/paper/2103.13109/) (2021)

## Abstract (arXiv)

An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to inconsistency in taxonomy and/or labeling policies of different datasets. To this end, we propose a knowledge distillation approach that also serves as a label space unification method for semantic segmentation. In short, a teacher model is trained on a source dataset with a given taxonomy, then used to pseudo-label additional data for which ground truth labels of a related label space exist. By mapping the related taxonomies to the source taxonomy, we create constraints within which the model can predict pseudo-labels. Using the improved pseudo-labels we train student models that consistently outperform their teachers in two challenging domains, namely urban and off-road driving. Our ground truth-corrected pseudo-labels span over 12 and 7 public datasets with 388.230 and 18.558 images for the urban and off-road domains, respectively, creating the largest compound datasets for autonomous driving to date.