Related papers: ProtoTTA: Prototype-Guided Test-Time Adaptation
Deep learning-based medical image segmentation models often face performance degradation when deployed across various medical centers, largely due to the discrepancies in data distribution. Test Time Adaptation (TTA) methods, which adapt…
Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. However, existing methods that rely on…
Wild Test-Time Adaptation (WTTA) is proposed to adapt a source model to unseen domains under extreme data scarcity and multiple shifts. Previous approaches mainly focused on sample selection strategies, while overlooking the fundamental…
Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such…
Distribution shift widely exists in medical images acquired from different medical centres and poses a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications. Test-time adaptation has proven…
Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…
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) 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…
Test-time adaptation (TTA) aims to adapt a pretrained model to distribution shifts using only unlabeled test data. While promising, existing methods like Tent suffer from instability and can catastrophically forget the source knowledge,…
Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…
Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without knowledge of the model training procedure. In online F-TTA, a…
Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to update at inference time without labeled data, typically via…
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refer to as trivial prototypes because they are trained to lie…
Reliable long-term decoding of surface electromyography (EMG) is hindered by signal drift caused by electrode shifts, muscle fatigue, and posture changes. While state-of-the-art models achieve high intra-session accuracy, their performance…
Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding.…
This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of…
Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for robustness in neural network systems when faced with…
Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt…
Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…