Related papers: DARDA: Domain-Aware Real-Time Dynamic Neural Netwo…
While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…
Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…
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 neural networks are known to be vulnerable to unseen data: they may wrongly assign high confidence stcores to out-distribuion samples. Recent works try to solve the problem using representation learning methods and specific metrics. In…
Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…
Moire patterns appear frequently when taking photos of digital screens, drastically degrading the image quality. Despite the advance of CNNs in image demoireing, existing networks are with heavy design, causing redundant computation burden…
Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performance, which include symmetric and asymmetric architectures.…
Federated domain adaptation (FDA) aims to collaboratively transfer knowledge from source clients (domains) to the related but different target client, without communicating the local data of any client. Moreover, the source clients have…
Sensor drift is a long-existing unpredictable problem that deteriorates the performance of gaseous substance recognition, calling for an antidrift domain adaptation algorithm. However, the prerequisite for traditional methods to achieve…
It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test…
Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground…
Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects…
Standard Convolutional Neural Network (CNN) designs rarely focus on the importance of explicitly capturing diverse features to enhance the network's performance. Instead, most existing methods follow an indirect approach of increasing or…
Neural network training is inherently sequential where the layers finish the forward propagation in succession, followed by the calculation and back-propagation of gradients (based on a loss function) starting from the last layer. The…
Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…
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…
In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as…
Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…
Accurate sleep stage classification across datasets remains challenging due to variability in EEG channel montages, sampling rates, recording environments, and subject populations. Although deep learning has shown considerable promise for…
Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to address the mismatch between the distributions of training and…