Related papers: Test-time augmentation improves efficiency in conf…
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…
Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scenarios. Test-time adaptation (TTA) provides a promising…
Conformal prediction, which makes no distributional assumptions about the data, has emerged as a powerful and reliable approach to uncertainty quantification in practical applications. The nonconformity measure used in conformal prediction…
Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…
Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical…
Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applications such as medical diagnosis. Usually, predictions are…
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. However, existing mainstream TTA methods, predominantly operating at batch level, often exhibit suboptimal performance in complex…
Test-time adaptation (TTA) enables efficient adaptation of deployed models, yet it often leads to poorly calibrated predictive uncertainty - a critical issue in high-stakes domains such as autonomous driving, finance, and healthcare.…
Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition…
Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a…
The development of large vision-language models, notably CLIP, has catalyzed research into effective adaptation techniques, with a particular focus on soft prompt tuning. Conjointly, test-time augmentation, which utilizes multiple augmented…
Test-Time Adaptation (TTA) adapts pre-trained models using only unlabeled test streams, requiring real-time inference and update without access to source data. We propose StructuralTest-time Alignment of Gradients (STAG), a lightweight…
While conformal predictors reap the benefits of rigorous statistical guarantees on their error frequency, the size of their corresponding prediction sets is critical to their practical utility. Unfortunately, there is currently a lack of…
Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples. This flexibility suits real deployments, yet…
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…
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) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation failures due to its reliance on blind adaptation to unknown test…
Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data. In this work, we propose a novel TTA approach for 3D point cloud classification, combining sampling…
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch…
Test-Time Adaptation (TTA) allows to update pre-trained models to changing data distributions at deployment time. While early work tested these algorithms for individual fixed distribution shifts, recent work proposed and applied methods…