# Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels

arXiv: https://arxiv.org/abs/1811.03542 · HTML: https://mlsanity.com/paper/1811.03542/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2018.

## Built on by (most cited first, 6 of 6)

- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2108.06682/) (2021)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [Joint Salient Object Detection and Camouflaged Object Detection via Uncertainty-aware Learning](https://mlsanity.com/paper/2307.04651/) (2023)
- [Domain-invariant Prototypes for Semantic Segmentation](https://mlsanity.com/paper/2208.06087/) (2022)
- [A General Divergence Modeling Strategy for Salient Object Detection](https://mlsanity.com/paper/2111.11827/) (2021)

## Abstract (arXiv)

Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent with the training data. In this paper, we show that by carefully presenting a mixture of labeled source domain and proxy-labeled target domain data to a network, we can achieve state-of-the-art unsupervised domain adaptation results. With our design, the network progressively learns features specific to the target domain using annotation from only the source domain. We generate proxy labels for the target domain using the network's own predictions. Our architecture then allows selective mining of easy samples from this set of proxy labels, and hard samples from the annotated source domain. We conduct a series of experiments with the GTA5, Cityscapes and BDD100k datasets on synthetic-to-real domain adaptation and geographic domain adaptation, showing the advantages of our method over baselines and existing approaches.