UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation

• URL: http://arxiv.org/abs/2405.09682v4
• Date: Fri, 03 Jan 2025 19:25:26 GMT
• Title: UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation
• Authors: Yachan Guo, Yi Xiao, Danna Xue, Jose Luis Gomez Zurita, Antonio M. Lopez,
• Abstract summary: Unsupervised Domain Adaptation (UDA) transfers knowledge from labeled synthetic data to unlabeled real-world data. UDA methods for synthetic to real-world domains (synth-to-real) show remarkable performance in tasks such as semantic segmentation and object detection. We introduce textbfUDA4Inst, a powerful framework for synth-to-real UDA in instance segmentation.
• Score: 5.982874955955054
• License:
• Abstract: Instance segmentation is crucial for autonomous driving but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled synthetic data to unlabeled real-world data. While UDA methods for synthetic to real-world domains (synth-to-real) show remarkable performance in tasks such as semantic segmentation and object detection, very few have been proposed for instance segmentation in vision-based autonomous driving. Moreover, existing methods rely on suboptimal baselines, which severely limits performance. We introduce \textbf{UDA4Inst}, a powerful framework for synth-to-real UDA in instance segmentation. Our framework enhances instance segmentation through \textit{Semantic Category Training} and \textit{Bidirectional Mixing Training}. With the Semantic Category Training method, semantically related classes are grouped and trained separately, enabling the generation of higher-quality pseudo-labels and improved segmentation performance. We further propose a bidirectional cross-domain data mixing strategy that combines instance-wise and patch-wise mixing techniques to effectively utilize data from both source and target domains, producing realistic composite images that improve the model's generalization performance. Extensive experiments demonstrate the effectiveness of our methods. Our approach establishes a new state-of-the-art on the SYNTHIA->Cityscapes benchmark with mAP 31.3. Notably, we are the first to report results on multiple novel synth-to-real instance segmentation datasets, using UrbanSyn and Synscapes as source domains while Cityscapes and KITTI360 serve as target domains. Our code will be released soon.

Related papers

• Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds [36.26157749644684]
  3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. We propose a density-guided translator (DGT) which translates point density between domains and integrates it into a two-stage self-training pipeline named DGT-ST. Experiments on two synthetic-to-real segmentation tasks demonstrate that DGT-ST outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-27T11:28:57Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers [96.51828911883456]
  Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation. We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
  arXiv  Detail & Related papers  (2022-12-14T15:54:15Z)
• Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection [86.98573522894961]
  We propose a framework that generalizes the components commonly used by Unsupervised Domain Adaptation (UDA) algorithms for detection. Specifically, we propose a novel UDA algorithm, ViSGA, that leverages the best design choices and introduces a simple but effective method to aggregate features at instance-level. We show that both similarity-based grouping and adversarial training allows our model to focus on coarsely aligning feature groups, without being forced to match all instances across loosely aligned domains.
  arXiv  Detail & Related papers  (2021-10-04T13:09:56Z)
• Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation [94.16816278191477]
  We present a framework for semi-adaptive and domain-supervised semantic segmentation. It is enhanced by self-supervised monocular depth estimation trained only on unlabeled image sequences. We validate the proposed model on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-08-28T01:33:38Z)
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation [71.77083272602525]
  UDA attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. We propose a contrastive learning approach that adapts category-wise centroids across domains. We extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels.
  arXiv  Detail & Related papers  (2021-05-05T11:55:53Z)
• Geometric Unsupervised Domain Adaptation for Semantic Segmentation [35.492127636785824]
  A simulator can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation. Our method scales well with the quality and quantity of synthetic data while also improving depth prediction.
  arXiv  Detail & Related papers  (2021-03-30T21:33:00Z)
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation [34.790169990156684]
  We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available. Two kinds of data mixing methods are proposed to reduce domain gap in both region-level and sample-level respectively. We can obtain two complementary domain-mixed teachers based on dual-level mixed data from holistic and partial views respectively.
  arXiv  Detail & Related papers  (2021-03-08T12:33:17Z)
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation [97.8552697905657]
  A key challenge of this task is how to alleviate the data distribution discrepancy between the source and target domains. We propose Alleviating Semantic-level Shift (ASS), which can successfully promote the distribution consistency from both global and local views. We apply our ASS to two domain adaptation tasks, from GTA5 to Cityscapes and from Synthia to Cityscapes.
  arXiv  Detail & Related papers  (2020-04-02T03:25:05Z)
• Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment [28.61782696432711]
  We propose a novel Unsupervised Domain Adaptation (UDA) strategy to address the domain shift issue between real world and synthetic representations. We show how the proposed strategy is able to obtain impressive performance in adapting a segmentation network trained on synthetic data to real world scenarios.
  arXiv  Detail & Related papers  (2020-01-14T10:12:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.