相关论文: Channel-Selective Normalization for Label-Shift Ro…

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower learning rates,…

Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result,…

When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…

Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to training data and processes, especially valuable in the context…

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for applications. Existing test-time…

Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and…

In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important tool of regularizing the distribution, batch normalization…

Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervised approaches. Recent efforts have been devoted to time…

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in practice: 1) only limited labeled samples are available due to expensive annotation costs over…

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g.…

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical…

While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This…

We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch…

Personalized federated learning algorithms have shown promising results in adapting models to various distribution shifts. However, most of these methods require labeled data on testing clients for personalization, which is usually…

There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme is required to prevent labeling errors from degrading the…