StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
- URL: http://arxiv.org/abs/2406.00275v1
- Date: Sat, 1 Jun 2024 02:41:34 GMT
- Title: StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
- Authors: Songhua Liu, Xin Jin, Xingyi Yang, Jingwen Ye, Xinchao Wang,
- Abstract summary: Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain.
State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data.
We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
- Score: 85.18995948334592
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging task. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data and thus increase robustness. Nevertheless, they have largely overlooked the underlying coherence between the augmented domains, which in turn leads to inferior results in real-world scenarios. In this paper, we propose a simple yet effective scheme, termed as \emph{StyDeSty}, to explicitly account for the alignment of the source and pseudo domains in the process of data augmentation, enabling them to interact with each other in a self-consistent manner and further giving rise to a latent domain with strong generalization power. The heart of StyDeSty lies in the interaction between a \emph{stylization} module for generating novel stylized samples using the source domain, and a \emph{destylization} module for transferring stylized and source samples to a latent domain to learn content-invariant features. The stylization and destylization modules work adversarially and reinforce each other. During inference, the destylization module transforms the input sample with an arbitrary style shift to the latent domain, in which the downstream tasks are carried out. Specifically, the location of the destylization layer within the backbone network is determined by a dedicated neural architecture search (NAS) strategy. We evaluate StyDeSty on multiple benchmarks and demonstrate that it yields encouraging results, outperforming the state of the art by up to {13.44%} on classification accuracy. Codes are available here: https://github.com/Huage001/StyDeSty.
Related papers
- GDO: Gradual Domain Osmosis [1.62060928868899]
We propose a new method called Gradual Domain Osmosis, which aims to solve the problem of smooth knowledge migration from source domain to target domain in Gradual Domain Adaptation (GDA)
Traditional Gradual Domain Adaptation methods mitigate domain bias by introducing intermediate domains and self-training strategies, but often face the challenges of inefficient knowledge migration or missing data in intermediate domains.
arXiv Detail & Related papers (2025-01-31T14:25:45Z) - Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
We introduce a novel single-domain object detection generalization method, named GoDiff.
By integrating pseudo-target domain data with source domain data, we diversify the training dataset.
Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
arXiv Detail & Related papers (2024-12-18T13:03:00Z) - Domain Expansion and Boundary Growth for Open-Set Single-Source Domain Generalization [70.02187124865627]
Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains.
We propose a novel learning approach based on domain expansion and boundary growth to expand the scarce source samples.
Our approach can achieve significant improvements and reach state-of-the-art performance on several cross-domain image classification datasets.
arXiv Detail & Related papers (2024-11-05T09:08:46Z) - xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing [21.37585797507323]
Cross-domain policy transfer methods mostly aim at learning domain correspondences or corrections to facilitate policy learning.
We propose the Cross-Domain Trajectory EDiting framework that employs a specially designed diffusion model for cross-domain trajectory adaptation.
Our proposed model architecture effectively captures the intricate dependencies among states, actions, and rewards, as well as the dynamics patterns within target data.
arXiv Detail & Related papers (2024-09-13T10:07:28Z) - Unsupervised Domain Adaptation for Semantic Segmentation via Low-level
Edge Information Transfer [27.64947077788111]
Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data adapt to real images.
Previous feature-level adversarial learning methods only consider adapting models on the high-level semantic features.
We present the first attempt at explicitly using low-level edge information, which has a small inter-domain gap, to guide the transfer of semantic information.
arXiv Detail & Related papers (2021-09-18T11:51:31Z) - 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) - Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model.
We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level.
Our method produces state-of-the-art results on the C-Driving dataset.
arXiv Detail & Related papers (2021-06-07T08:38:41Z) - Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain
Adaptive Semantic Segmentation [102.42638795864178]
We propose a principled meta-learning based approach to OCDA for semantic segmentation.
We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner.
A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code.
We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
arXiv Detail & Related papers (2020-12-15T13:21:54Z) - 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)
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.