# Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.08278 · HTML: https://mlsanity.com/paper/2012.08278/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [Source-Free Open Compound Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2106.03422/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2207.09045/) (2022)
- [Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation](https://mlsanity.com/paper/2309.16127/) (2023)
- [Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2202.04287/) (2022)
- [Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels](https://mlsanity.com/paper/2208.02804/) (2022)
- [VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions](https://mlsanity.com/paper/2211.12256/) (2022)
- [Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning](https://mlsanity.com/paper/2203.10395/) (2022)
- [Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation](https://mlsanity.com/paper/2401.09496/) (2024)
- [Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation](https://mlsanity.com/paper/2111.10339/) (2021)
- [Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction](https://mlsanity.com/paper/2305.07269/) (2023)
- [Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation](https://mlsanity.com/paper/2312.06331/) (2023)
- [SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2405.14278/) (2024)
- [Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization](https://mlsanity.com/paper/2409.02486/) (2024)
- [SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement](https://mlsanity.com/paper/2412.06352/) (2024)
- [Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation](https://mlsanity.com/paper/2408.07527/) (2024)
- [AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation](https://mlsanity.com/paper/2412.02280/) (2024)

## Abstract (arXiv)

Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. Our approach consists of four key steps. First, we cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. Then, different sub-target domains are split into independent branches, for which batch normalization parameters are learnt to treat them independently. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. Meanwhile, we learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization. We validate the benefits of our approach by extensive experiments on synthetic-to-real knowledge transfer benchmark datasets, where we achieve the state-of-the-art performance in both compound and open domains.