Normalization Perturbation: A Simple Domain Generalization Method for
Real-World Domain Shifts
- URL: http://arxiv.org/abs/2211.04393v2
- Date: Wed, 9 Nov 2022 02:53:31 GMT
- Title: Normalization Perturbation: A Simple Domain Generalization Method for
Real-World Domain Shifts
- Authors: Qi Fan, Mattia Segu, Yu-Wing Tai, Fisher Yu, Chi-Keung Tang, Bernt
Schiele, Dengxin Dai
- Abstract summary: Real-world domain styles can vary substantially due to environment changes and sensor noises.
Deep models only know the training domain style.
We propose Normalization Perturbation to overcome this domain style overfitting problem.
- Score: 133.99270341855728
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Improving model's generalizability against domain shifts is crucial,
especially for safety-critical applications such as autonomous driving.
Real-world domain styles can vary substantially due to environment changes and
sensor noises, but deep models only know the training domain style. Such domain
style gap impedes model generalization on diverse real-world domains. Our
proposed Normalization Perturbation (NP) can effectively overcome this domain
style overfitting problem. We observe that this problem is mainly caused by the
biased distribution of low-level features learned in shallow CNN layers. Thus,
we propose to perturb the channel statistics of source domain features to
synthesize various latent styles, so that the trained deep model can perceive
diverse potential domains and generalizes well even without observations of
target domain data in training. We further explore the style-sensitive channels
for effective style synthesis. Normalization Perturbation only relies on a
single source domain and is surprisingly effective and extremely easy to
implement. Extensive experiments verify the effectiveness of our method for
generalizing models under real-world domain shifts.
Related papers
- 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) - StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
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.
arXiv Detail & Related papers (2024-06-01T02:41:34Z) - Non-stationary Domain Generalization: Theory and Algorithm [11.781050299571692]
In this paper, we study domain generalization in non-stationary environment.
We first examine the impact of environmental non-stationarity on model performance.
Then, we propose a novel algorithm based on adaptive invariant representation learning.
arXiv Detail & Related papers (2024-05-10T21:32:43Z) - DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
Causality has been combined with machine learning to produce robust representations for domain generalization.
We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy.
We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
arXiv Detail & Related papers (2024-02-29T07:09:01Z) - A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain.
The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance.
We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
arXiv Detail & Related papers (2023-08-02T03:16:12Z) - Cross Contrasting Feature Perturbation for Domain Generalization [11.863319505696184]
Domain generalization aims to learn a robust model from source domains that generalize well on unseen target domains.
Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains.
We propose an online one-stage Cross Contrasting Feature Perturbation framework to simulate domain shift.
arXiv Detail & Related papers (2023-07-24T03:27:41Z) - Single Domain Dynamic Generalization for Iris Presentation Attack
Detection [41.126916126040655]
Iris presentation generalization has achieved great success under intra-domain settings but easily degrades on unseen domains.
We propose a Single Domain Dynamic Generalization (SDDG) framework, which exploits domain-invariant and domain-specific features on a per-sample basis.
The proposed method is effective and outperforms the state-of-the-art on LivDet-Iris 2017 dataset.
arXiv Detail & Related papers (2023-05-22T07:54:13Z) - 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) - Federated and Generalized Person Re-identification through Domain and
Feature Hallucinating [88.77196261300699]
We study the problem of federated domain generalization (FedDG) for person re-identification (re-ID)
We propose a novel method, called "Domain and Feature Hallucinating (DFH)", to produce diverse features for learning generalized local and global models.
Our method achieves the state-of-the-art performance for FedDG on four large-scale re-ID benchmarks.
arXiv Detail & Related papers (2022-03-05T09:15:13Z) - Learning causal representations for robust domain adaptation [31.261956776418618]
In many real-world applications, target domain data may not always be available.
In this paper, we study the cases where at the training phase the target domain data is unavailable.
We propose a novel Causal AutoEncoder (CAE), which integrates deep autoencoder and causal structure learning into a unified model.
arXiv Detail & Related papers (2020-11-12T11:24:03Z)
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.