Zobrazeno 1 - 10
of 138 759
pro vyhledávání: '"Test Time"'
Publikováno v:
AAAI 2025
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 optimizatio
Externí odkaz:
http://arxiv.org/abs/2412.16901
Publikováno v:
S. Li, Z. Wang, H. Luo, L. Ding and D. Wu, T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs, IEEE Trans. on Biomedical Engineering, 71(2):423-432, 2024
Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-
Externí odkaz:
http://arxiv.org/abs/2412.07228
Recent text-to-image generation favors various forms of spatial conditions, e.g., masks, bounding boxes, and key points. However, the majority of the prior art requires form-specific annotations to fine-tune the original model, leading to poor test-t
Externí odkaz:
http://arxiv.org/abs/2501.01368
Capitalizing on the complementary advantages of generative and discriminative models has always been a compelling vision in machine learning, backed by a growing body of research. This work discloses the hidden semantic structure within score-based g
Externí odkaz:
http://arxiv.org/abs/2501.00873
One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However, previous tes
Externí odkaz:
http://arxiv.org/abs/2412.17306
Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still struggle to handle data distribution shifts, leading to performance degrad
Externí odkaz:
http://arxiv.org/abs/2412.10871
Autor:
Feng, Chun-Mei, He, Yuanyang, Zou, Jian, Khan, Salman, Xiong, Huan, Li, Zhen, Zuo, Wangmeng, Goh, Rick Siow Mong, Liu, Yong
Publikováno v:
International Journal of Computer Vision, 2025
Existing test-time prompt tuning (TPT) methods focus on single-modality data, primarily enhancing images and using confidence ratings to filter out inaccurate images. However, while image generation models can produce visually diverse images, single-
Externí odkaz:
http://arxiv.org/abs/2412.09706
Autor:
Lee, Yoonho, Williams, Jonathan, Marklund, Henrik, Sharma, Archit, Mitchell, Eric, Singh, Anikait, Finn, Chelsea
Large pretrained models often struggle with underspecified tasks -- situations where the training data does not fully define the desired behavior. For example, chatbots must handle diverse and often conflicting user preferences, requiring adaptabilit
Externí odkaz:
http://arxiv.org/abs/2412.08812
This paper introduces Test-time Correction (TTC) system, a novel online 3D detection system designated for online correction of test-time errors via human feedback, to guarantee the safety of deployed autonomous driving systems. Unlike well-studied o
Externí odkaz:
http://arxiv.org/abs/2412.07768
Deep learning models often struggle with generalization when deploying on real-world data, due to the common distributional shift to the training data. Test-time adaptation (TTA) is an emerging scheme used at inference time to address this issue. In
Externí odkaz:
http://arxiv.org/abs/2412.07980