Corpus ID: 230437520

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},
  • Xin Jin, Cuiling Lan, +1 author Zhibo Chen
  • Published 2021
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING


    Style Normalization and Restitution for Generalizable Person Re-Identification
    • 24
    • PDF
    Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
    • 53
    • PDF
    Deeper, Broader and Artier Domain Generalization
    • 224
    • Highly Influential
    • PDF
    Unified Deep Supervised Domain Adaptation and Generalization
    • 235
    • Highly Influential
    • PDF
    FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
    • 342
    • PDF
    Domain Adaptive Faster R-CNN for Object Detection in the Wild
    • 277
    • Highly Influential
    • PDF
    CyCADA: Cycle-Consistent Adversarial Domain Adaptation
    • 1,059
    • PDF
    Semi-Supervised Domain Adaptation via Minimax Entropy
    • 95
    • PDF
    Return of Frustratingly Easy Domain Adaptation
    • 679
    • PDF
    ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
    • 165
    • PDF