Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive
Learning
- URL: http://arxiv.org/abs/2104.11056v1
- Date: Thu, 22 Apr 2021 13:39:12 GMT
- Title: Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive
Learning
- Authors: Weizhe Liu, David Ferstl, Samuel Schulter, Lukas Zebedin, Pascal Fua,
Christian Leistner
- Abstract summary: We leverage contrastive learning to bridge the domain gap by aligning the features of structurally similar label patches across domains.
Our approach consistently outperforms state-of-the-art unsupervised and semi-supervised methods on two challenging domain adaptive segmentation tasks.
- Score: 62.7588467386166
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce a novel approach to unsupervised and semi-supervised domain
adaptation for semantic segmentation. Unlike many earlier methods that rely on
adversarial learning for feature alignment, we leverage contrastive learning to
bridge the domain gap by aligning the features of structurally similar label
patches across domains. As a result, the networks are easier to train and
deliver better performance. Our approach consistently outperforms
state-of-the-art unsupervised and semi-supervised methods on two challenging
domain adaptive segmentation tasks, particularly with a small number of target
domain annotations. It can also be naturally extended to weakly-supervised
domain adaptation, where only a minor drop in accuracy can save up to 75% of
annotation cost.
Related papers
- Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with
Point Supervision via Active Selection [81.703478548177]
Training models dedicated to semantic segmentation require a large amount of pixel-wise annotated data.
Unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data.
Previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data.
We propose a new domain adaptation framework for semantic segmentation with annotated points via active selection.
arXiv Detail & Related papers (2022-06-01T01:52:28Z) - Towards Fewer Annotations: Active Learning via Region Impurity and
Prediction Uncertainty for Domain Adaptive Semantic Segmentation [19.55572909866489]
We propose a region-based active learning approach for semantic segmentation under a domain shift.
Our algorithm, Active Learning via Region Impurity and Prediction Uncertainty (AL-RIPU), introduces a novel acquisition strategy characterizing the spatial adjacency of image regions.
Our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-11-25T06:40:58Z) - Shallow Features Guide Unsupervised Domain Adaptation for Semantic
Segmentation at Class Boundaries [21.6953660626021]
Deep neural networks fail to generalize towards new domains when performing synthetic-to-real adaptation.
In this work, we present a novel low-level adaptation strategy that allows us to obtain sharp predictions.
We also introduce an effective data augmentation that alleviates the noise typically present at semantic boundaries when employing pseudo-labels for self-training.
arXiv Detail & Related papers (2021-10-06T15:05:48Z) - Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training
for Road Segmentation of Remote Sensing Images [93.50240389540252]
Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials.
We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field.
Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-08-28T09:29:14Z) - Adapting Segmentation Networks to New Domains by Disentangling Latent
Representations [14.050836886292869]
Domain adaptation approaches have come into play to transfer knowledge acquired on a label-abundant source domain to a related label-scarce target domain.
We propose a novel performance metric to capture the relative efficacy of an adaptation strategy compared to supervised training.
arXiv Detail & Related papers (2021-08-06T09:43:07Z) - 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) - Latent Space Regularization for Unsupervised Domain Adaptation in
Semantic Segmentation [14.050836886292869]
We introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation.
We verify the effectiveness of such methods in the autonomous driving setting.
arXiv Detail & Related papers (2021-04-06T16:07:22Z) - Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining
and Consistency [93.89773386634717]
Visual domain adaptation involves learning to classify images from a target visual domain using labels available in a different source domain.
We show that in the presence of a few target labels, simple techniques like self-supervision (via rotation prediction) and consistency regularization can be effective without any adversarial alignment to learn a good target classifier.
Our Pretraining and Consistency (PAC) approach, can achieve state of the art accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets.
arXiv Detail & Related papers (2021-01-29T18:40:17Z) - Domain Adaptation for Semantic Parsing [68.81787666086554]
We propose a novel semantic for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain.
Our semantic benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages.
Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies.
arXiv Detail & Related papers (2020-06-23T14:47:41Z)
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.