相关论文: Speed-enhanced Subdomain Adaptation Regression for…

Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to…

Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the…

In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance to enhance the reliability of deep neural networks. In this paper, we propose a lightweight, loss-function-free,…

Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tuning while neglecting cross-modal interaction, leading to…

Aiming to generalize the label knowledge from a source domain with continuous outputs to an unlabeled target domain, Domain Adaptation Regression (DAR) is developed for complex practical learning problems. However, due to the continuity…

Recent years have witnessed the success of introducing deep learning models to time series forecasting. From a data generation perspective, we illustrate that existing models are susceptible to distribution shifts driven by temporal…

High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose a self-supervised domain adaptation method, based upon an iterative pseudo-forced alignment algorithm. The produced alignments are…

Continual test-time domain adaptation (CTTA) aims to adjust models so that they can perform well over time across non-stationary environments. While previous methods have made considerable efforts to optimize the adaptation process, a…

Unsupervised domain adaptation has increasingly gained interest in medical image computing, aiming to tackle the performance degradation of deep neural networks when being deployed to unseen data with heterogeneous characteristics. In this…

Brain-computer interfaces (BCIs) allow direct communication between the brain and external devices, frequently using electroencephalography (EEG) to record neural activity. Dimensionality reduction and structured regularization are…

The advent of neuralmorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution.However, this imaging attribute necessitates considerable resources for binary…

The central problem in biomedical imaging are batch effects: systematic technical variations unrelated to the biological signal of interest. These batch effects critically undermine experimental reproducibility and are the primary cause of…

We study source-free unsupervised domain adaptation (SFUDA) for semantic segmentation, which aims to adapt a source-trained model to the target domain without accessing the source data. Many works have been proposed to address this…

The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data…

The variability in EEG signals between different individuals poses a significant challenge when implementing brain-computer interfaces (BCI). Commonly proposed solutions to this problem include deep learning models, due to their increased…

Machine learning and deep learning advancements have boosted Brain-Computer Interface (BCI) performance, but their wide-scale applicability is limited due to factors like individual health, hardware variations, and cultural differences…

Domain adaptation methods aim to bridge the gap between datasets by enabling knowledge transfer across domains, reducing the need for additional expert annotations. However, many approaches struggle with reliability in the target domain, an…

Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance…

Domain adaptation (DA) is used for adaptively obtaining labels of an unprocessed data set with a given related, but different labelled data set. Subspace alignment (SA), a representative DA algorithm, attempts to find a linear…

Pervasive localization is essential for continuous tracking applications, yet existing solutions face challenges in balancing power consumption and accuracy. GPS, while precise, is impractical for continuous tracking of micro-assets due to…