Related papers: Neural Collapse in Test-Time Adaptation
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…
Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to…
This paper focuses on the Continual Test-Time Adaptation (CTTA) task, aiming to enable an agent to continuously adapt to evolving target domains while retaining previously acquired domain knowledge for effective reuse when those domains…
Pretrained vision-language models (VLMs) like CLIP show strong zero-shot performance but struggle with generalization under distribution shifts. Test-Time Adaptation (TTA) addresses this by adapting VLMs to unlabeled test data in new…
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,…
Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture,…
Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing…
Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, 3) online imbalanced label distribution shifts. This is often a key obstacle…
Real-world application models are commonly deployed in dynamic environments, where the target domain distribution undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually…
Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the…
The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…
Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the…
Test-time Adaptation (TTA) aims to improve model performance when the model encounters domain changes after deployment. The standard TTA mainly considers the case where the target domain is static, while the continual TTA needs to undergo a…
Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA…
Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation…
Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corrupted point clouds. LiDAR data, for instance, can be affected…
Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA methods further restrict…
The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished. In this terminal phase…
Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or…
Quantizing deep models prior to deployment is a widely adopted technique to speed up inference for various real-time applications, such as autonomous driving. However, quantized models often suffer from severe performance degradation in…