paper-with-me

홈 › Papers

AdvST: Revisiting Data Augmentations for Single Domain Generalization

2023-12-20 · Guangtao Zheng, Mengdi Huai, Aidong Zhang

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard augmentations, such as translate, or invert, has not been fully exploited in SDG; practically, these augmentations are used as a part of a data preprocessing procedure. Although it is intuitive to use many such augmentations to boost the robustness of a model to out-of-distribution domain shifts, we lack a principled approach to harvest the benefit brought from multiple these augmentations. Here, we conceptualize standard data augmentations with learnable parameters as semantics transformations that can manipulate certain semantics of a sample, such as the geometry or color of an image. Then, we propose Adversarial learning with Semantics Transformations (AdvST) that augments the source domain data with semantics transformations and learns a robust model with the augmented data. We theoretically show that AdvST essentially optimizes a distributionally robust optimization objective defined on a set of semantics distributions induced by the parameters of semantics transformations. We demonstrate that AdvST can produce samples that expand the coverage on target domain data. Compared with the state-of-the-art methods, AdvST, despite being a simple method, is surprisingly competitive and achieves the best average SDG performance on the Digits, PACS, and DomainNet datasets. Our code is available at https://github.com/gtzheng/AdvST.

📄 PDF Abstract BibTeX arXiv:2312.12720

Code (1)

gtzheng/advst 공식 구현 pytorch

Tasks

Data AugmentationDomain Generalization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

2022-07-11 · Zhun Zhong, Yuyang Zhao, Gim Hee Lee, Nicu Sebe

In this paper, we consider the problem of domain generalization in semantic segmentation, which aims to learn a robust model using only labeled synthetic (source) data. The model is expected to perform well on unseen rea…

Domain Generalizationimage-classificationImage ClassificationScene Segmentation+1

Adversarial Style Augmentation for Domain Generalization

2023-01-30 · Yabin Zhang, Bin Deng, Ruihuang Li, Kui Jia 외

It is well-known that the performance of well-trained deep neural networks may degrade significantly when they are applied to data with even slightly shifted distributions. Recent studies have shown that introducing cert…

domain classificationDomain GeneralizationRetrieval

Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training

2024-02-18 · Huayi Zhou, Mukun Luo, Fei Jiang, Yue Ding 외

The 2D human pose estimation (HPE) is a basic visual problem. However, its supervised learning requires massive keypoint labels, which is labor-intensive to collect. Thus, we aim at boosting a pose estimator by excavatin…

2D Human Pose EstimationData AugmentationPose Estimation

Adversarial Bayesian Augmentation for Single-Source Domain Generalization

2023-07-18 · ICCV 2023 1 · Sheng Cheng, Tejas Gokhale, Yezhou Yang

Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such d…

Data AugmentationDomain GeneralizationPhoto to Rest GeneralizationSingle-Source Domain Generalization

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning

2023-09-21 · NeurIPS 2023 11

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-dest…