Source-Free Open Compound Domain Adaptation in Semantic Segmentation

Zhao, Yang; Zhang, Zhong; Luo, Zhengxiu; Lee, Gim Hee; Sebe, Nicu

doi:10.48550/arxiv.2106.03422

Cited by 2 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, MixStyle is still a versatile approach given its broad applications. It is also worth mentioning that since our conference publication, MixStyle has been extended to other applications, such as vehicle re-identification [82] and semantic segmentation [83].…”

Section: Discussionmentioning

confidence: 99%

MixStyle Neural Networks for Domain Generalization and Adaptation

Zhou,

Yang,

Qiao

et al. 2021

Preprint

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) often have poor generalization performance under domain shift. One way to improve domain generalization is to collect diverse source data from multiple relevant domains so that a CNN model is allowed to learn more domain-invariant, and hence generalizable representations. In this work, we address domain generalization with MixStyle, a plug-and-play, parameter-free module that is simply inserted to shallow CNN layers and requires no modification to training objectives. Specifically, MixStyle probabilistically mixes feature statistics between instances. This idea is inspired by the observation that visual domains can often be characterized by image styles which are in turn encapsulated within instance-level feature statistics in shallow CNN layers. Therefore, inserting MixStyle modules in effect synthesizes novel domains albeit in an implicit way. MixStyle is not only simple and flexible, but also versatile-it can be used for problems whereby unlabeled images are available, such as semi-supervised domain generalization and unsupervised domain adaptation, with a simple extension to mix feature statistics between labeled and pseudo-labeled instances. We demonstrate through extensive experiments that MixStyle can significantly boost the out-of-distribution generalization performance across a wide range of tasks including object recognition, instance retrieval, and reinforcement learning.

show abstract

Section: Discussionmentioning

confidence: 99%

MixStyle Neural Networks for Domain Generalization and Adaptation

Zhou,

Yang,

Qiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In more detail, we propose the following sequence of steps (see also Figure 1): (2021) and Liu et al (2021). At the same time, we can fully profit from all advances in the field of pseudo-label rectification (Prabhu et al, 2021;Wu et al, 2021;Zhang et al, 2021;Zhao et al, 2021), applying those to pseudo-labels generated by the PE network.…”

Section: Methodsmentioning

confidence: 99%

From Shallow to Deep: Exploiting Feature-Based Classifiers for Domain Adaptation in Semantic Segmentation

Matskevych¹,

Wolny²,

Pape³

et al. 2022

Front. Comput. Sci.

View full text Add to dashboard Cite

The remarkable performance of Convolutional Neural Networks on image segmentation tasks comes at the cost of a large amount of pixelwise annotated images that have to be segmented for training. In contrast, feature-based learning methods, such as the Random Forest, require little training data, but rarely reach the segmentation accuracy of CNNs. This work bridges the two approaches in a transfer learning setting. We show that a CNN can be trained to correct the errors of the Random Forest in the source domain and then be applied to correct such errors in the target domain without retraining, as the domain shift between the Random Forest predictions is much smaller than between the raw data. By leveraging a few brushstrokes as annotations in the target domain, the method can deliver segmentations that are sufficiently accurate to act as pseudo-labels for target-domain CNN training. We demonstrate the performance of the method on several datasets with the challenging tasks of mitochondria, membrane and nuclear segmentation. It yields excellent performance compared to microscopy domain adaptation baselines, especially when a significant domain shift is involved.

show abstract

Source-Free Open Compound Domain Adaptation in Semantic Segmentation

Cited by 2 publications

References 31 publications

MixStyle Neural Networks for Domain Generalization and Adaptation

MixStyle Neural Networks for Domain Generalization and Adaptation

From Shallow to Deep: Exploiting Feature-Based Classifiers for Domain Adaptation in Semantic Segmentation

Contact Info

Product

Resources

About