Related papers: Train/Test-Time Adaptation with Retrieval

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…

Unsupervised domain adaptation methods aim to generalize well on unlabeled test data that may have a different (shifted) distribution from the training data. Such methods are typically developed on image data, and their application to time…

Human Activity Recognition (HAR) models often suffer from performance degradation in real-world applications due to distribution shifts in activity patterns across individuals. Test-Time Adaptation (TTA) is an emerging learning paradigm…

The recent developments of deep learning models that capture complex temporal patterns of crop phenology have greatly advanced crop classification from Satellite Image Time Series (SITS). However, when applied to target regions spatially…

Sequential recommendation is essential in modern recommender systems, aiming to predict the next item a user may interact with based on their historical behaviors. However, real-world scenarios are often dynamic and subject to shifts in…

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable and difficult,…

To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform…

Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with unstructured data, their efficacy with structured data has…

Anomaly detection on time series data is increasingly common across various industrial domains that monitor metrics in order to prevent potential accidents and economic losses. However, a scarcity of labeled data and ambiguous definitions…

The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due…

Remote sensing text--image retrieval (RSTIR) aims to retrieve the matched remote sensing (RS) images from the database according to the descriptive text. Recently, the rapid development of large visual-language pre-training models provides…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments…

Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data.…

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a…

Real-world time series often exhibit a non-stationary nature, degrading the performance of pre-trained forecasting models. Test-Time Adaptation (TTA) addresses this by adjusting models during inference, but existing methods typically update…

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling…

Human mesh recovery from single images remains challenging due to inherent depth ambiguity and limited generalization across domains. While recent methods combine regression and optimization approaches, they struggle with poor…

In the pursuit of robust autonomous driving systems, models trained on real-world datasets often struggle to adapt to new environments, particularly when confronted with corner cases such as extreme weather conditions. Collecting these…