相关论文: MixStyle Neural Networks for Domain Generalization…

Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features. Existing methods diversify images in the source domain by adding complex or even…

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

Objective: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but…

The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a clear motivation in contexts where there are…

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant…

Mixup is a widely adopted data augmentation technique known for enhancing the generalization of machine learning models by interpolating between data points. Despite its success and popularity, limited attention has been given to…

Considering the scarcity of medical data, most datasets in medical image analysis are an order of magnitude smaller than those of natural images. However, most Network Architecture Search (NAS) approaches in medical images focused on…

Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant…

Multimodal and multi-domain stylization are two important problems in the field of image style transfer. Currently, there are few methods that can perform both multimodal and multi-domain stylization simultaneously. In this paper, we…

Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data…

In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a…

We propose a simple domain adaptation method for neural networks in a supervised setting. Supervised domain adaptation is a way of improving the generalization performance on the target domain by using the source domain dataset, assuming…

Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…

In domain generalization (DG), the target domain is unknown when the model is being trained, and the trained model should successfully work on an arbitrary (and possibly unseen) target domain during inference. This is a difficult problem,…

For medical image analysis, segmentation models trained on one or several domains lack generalization ability to unseen domains due to discrepancies between different data acquisition policies. We argue that the degeneration in segmentation…

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we…