相关论文: NC-TTT: A Noise Contrastive Approach for Test-Time…

Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…

Deep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization, unfortunately, leads to performance degradation. Recently, virtual adversarial training (VAT)…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically…

Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often…

Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of…

We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization…

Target domain pseudo-labelling has shown effectiveness in unsupervised domain adaptation (UDA). However, pseudo-labels of unlabeled target domain data are inevitably noisy due to the distribution shift between source and target domains.…

Standard uncertainty estimation techniques, such as dropout, often struggle to clearly distinguish reliable predictions from unreliable ones. We attribute this limitation to noisy classifier weights, which, while not impairing overall…

Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation…

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the…

In this paper, we study the application of Test-Time Training (TTT) as a solution to handling distribution shifts in speech applications. In particular, we introduce distribution-shifts to the test datasets of standard speech-classification…

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that…

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test…

Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain…