Related papers: Decoupled Prototype Learning for Reliable Test-Tim…
There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…
Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue…
Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during the training. Adapting the models using annotated data from…
Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…
Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain…
Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected…
Unsupervised domain adaptation (UDA) for time series data remains a critical challenge in deep learning, with traditional pseudo-labeling strategies failing to capture temporal patterns and channel-wise shifts between domains, producing…
We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived…
Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…
Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches…
The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resulting labels may be class imbalanced, noisy or human biased.…
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…
The goal of test-time adaptation is to adapt a source-pretrained model to a continuously changing target domain without relying on any source data. Typically, this is either done by updating the parameters of the model (model adaptation)…
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…
Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et…
Traditional test-time adaptation (TTA) methods face significant challenges in adapting to dynamic environments characterized by continuously changing long-term target distributions. These challenges primarily stem from two factors:…
Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong…
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…
Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat…