Style Normalization and Restitution for DomainGeneralization and Adaptation

  title={Style Normalization and Restitution for DomainGeneralization and Adaptation},
  author={Xin Jin and Cuiling Lan and Wenjun Zeng and Zhibo Chen},
For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are usually style differences between the training images and the testing images. An effective domain generalizable model is expected to be able to learn feature representations that are both generalizable and discriminative. In this paper, we design a novel Style… 
Mitigating Domain Mismatch in Face Recognition Using Style Matching
Generalizing to Unseen Domains: A Survey on Domain Generalization
This paper provides a formal definition of domain generalization and discusses several related fields, and categorizes recent algorithms into three classes and present them in detail: data manipulation, representation learning, and learning strategy, each of which contains several popular algorithms.
Towards Out-Of-Distribution Generalization: A Survey
This paper serves as the first effort to systematically and comprehensively discuss the OOD generalization problem, from the definition, methodology, evaluation to the implications and future directions.
Calibrated Feature Decomposition for Generalizable Person Re-Identification
A simple yet effective Calibrated Feature Decomposition (CFD) module that focuses on improving the generalization capacity for person re-identification through a more judicious feature decomposition and reinforcement strategy.
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
This survey is an effort to summarize five years of this incredibly rapidly growing field, which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments.
Invariant Information Bottleneck for Domain Generalization
IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.
NICO++: Towards Better Benchmarking for Domain Generalization
A large-scale benchmark with extensive labeled domains named NICO ++ is proposed along with more rational evaluation methods for comprehensively evaluating DG algorithms to prove that limited concept shift and significant covariate shift favor the evaluation capability for generalization.
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
A novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person reidentification is proposed, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
This work builds upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets, and introduces a simple yet effective framework CDCL, for domain alignment.


Style Normalization and Restitution for Generalizable Person Re-Identification
The aim of this paper is to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains, and to enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features.
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
The proposed Batch-Instance Normalization (BIN) module is easily incorporated into existing network architectures such as Residual Networks, and surprisingly improves the recognition performance in various scenarios.
Deeper, Broader and Artier Domain Generalization
This paper builds upon the favorable domain shift-robust properties of deep learning methods, and develops a low-rank parameterized CNN model for end-to-end DG learning that outperforms existing DG alternatives.
Unified Deep Supervised Domain Adaptation and Generalization
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models by reverting to point-wise surrogates of distribution distances and similarities by exploiting the Siamese architecture.
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets.
Domain Adaptive Faster R-CNN for Object Detection in the Wild
This work builds on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy, based on $$-divergence theory.
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
A novel discriminatively-trained Cycle-Consistent Adversarial Domain Adaptation model that adapts representations at both the pixel-level and feature-level, enforces cycle-consistency while leveraging a task loss, and does not require aligned pairs is proposed.
Semi-Supervised Domain Adaptation via Minimax Entropy
A novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model for semi-supervised domain adaptation (SSDA) setting, setting a new state of the art for SSDA.
Return of Frustratingly Easy Domain Adaptation
This work proposes a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL), which minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels.
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
This paper presents a simple yet effective approach that for the first time enables arbitrary style transfer in real-time, comparable to the fastest existing approach, without the restriction to a pre-defined set of styles.