# Category-Adaptive Domain Adaptation for Semantic Segmentation

arXiv: https://arxiv.org/abs/2103.15467 · HTML: https://mlsanity.com/paper/2103.15467/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [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)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Source Free Domain Adaptation with Image Translation](https://mlsanity.com/paper/2008.07514/) (2020)
- [High-Resolution Network for Photorealistic Style Transfer](https://mlsanity.com/paper/1904.11617/) (2019)
- [Correntropy Induced L2 Graph for Robust Subspace Clustering](https://mlsanity.com/paper/1501.04277/) (2015)

## Built on by (most cited first, 2 of 2)

- [Refined Pseudo labeling for Source-free Domain Adaptive Object Detection](https://mlsanity.com/paper/2303.03728/) (2023)
- [Enhancing cross-domain detection: adaptive class-aware contrastive transformer](https://mlsanity.com/paper/2401.13264/) (2024)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) becomes more and more popular in tackling real-world problems without ground truth of the target domain. Though tedious annotation work is not required, UDA unavoidably faces two problems: 1) how to narrow the domain discrepancy to boost the transferring performance; 2) how to improve pseudo annotation producing mechanism for self-supervised learning (SSL). In this paper, we focus on UDA for semantic segmentation task. Firstly, we introduce adversarial learning into style gap bridging mechanism to keep the style information from two domains in the similar space. Secondly, to keep the balance of pseudo labels on each category, we propose a category-adaptive threshold mechanism to choose category-wise pseudo labels for SSL. The experiments are conducted using GTA5 as the source domain, Cityscapes as the target domain. The results show that our model outperforms the state-of-the-arts with a noticeable gain on cross-domain adaptation tasks.