Related papers: Neural Collapse in Test-Time Adaptation
Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot recognition by comparing image embeddings to text-derived class prototypes. However, under domain shift, they suffer from feature drift, class-prior mismatch, and severe…
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…
Test-time adaptation (TTA) enhances model robustness by enabling adaptation to target distributions that differ from training distributions, improving real-world generalizability. However, most existing TTA approaches focus on adjusting the…
Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which…
Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the…
Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…
Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a…
In this paper, we seek to develop a versatile test-time adaptation (TTA) objective for a variety of tasks - classification and regression across image-, object-, and pixel-level predictions. We achieve this through a self-bootstrapping…
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…
Despite domain generalization (DG) has significantly addressed the performance degradation of pre-trained models caused by domain shifts, it often falls short in real-world deployment. Test-time adaptation (TTA), which adjusts a learned…
The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time training (TTT), which adapts the learned model with test data,…
Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…
Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts remain a major challenge, leading to performance degradation…
Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this…
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…
Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift…
Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted…
Hyperspectral image (HSI) classification models are highly sensitive to distribution shifts caused by real-world degradations such as noise, blur, compression, and atmospheric effects. To address this challenge, we propose HyperTTA…
Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despite its empirical success, the learnability of TTA under non-stationary streams remains…
Test-time adaptation (TTA) has emerged as a promising solution to address performance decay due to unforeseen distribution shifts between training and test data. While recent TTA methods excel in adapting to test data variations, such…