Related papers: Multi-Stream Cellular Test-Time Adaptation of Real…
Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial…
In dynamic environments, unfamiliar objects and distribution shifts are often encountered, which challenge the generalization abilities of the deployed trained models. This work addresses Incremental Test Time Adaptation of Vision Language…
Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts in downstream tasks, particularly in the absence of labeled data. Test-Time Adaptation (TTA) addresses…
In many real-world scenarios, distribution shifts exist in the streaming data across time steps. Many complex sequential data can be effectively divided into distinct regimes that exhibit persistent dynamics. Discovering the shifted…
Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…
Stream workflow application such as online anomaly detection or online traffic monitoring, integrates multiple streaming big data applications into data analysis pipeline. This application can be highly dynamic in nature, where the data…
Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which…
Nowadays, IoT devices have an enlarging scope of activities spanning from sensing, computing to acting and even more, learning, reasoning and planning. As the number of IoT applications increases, these objects are becoming more and more…
Online adaptation to distribution shifts in satellite image segmentation stands as a crucial yet underexplored problem. In this paper, we address source-free and online domain adaptation, i.e., test-time adaptation (TTA), for satellite…
Data stream learning is a very relevant paradigm because of the increasing real-world scenarios generating data at high velocities and in unbounded sequences. Stream learning aims at developing models that can process instances as they…
Massive Machine Type Communication (mMTC) to serve billions of IoT devices is considered to open a potential new market for the next generation cellular network. Legacy cellular networks cannot meet the requirements of emerging mMTC…
Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing…
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…
Traffic signal control is a critical challenge in urban transportation, requiring coordination among multiple intersections to optimize network-wide traffic flow. While reinforcement learning has shown promise for adaptive signal control,…
Test time Adaptation is a promising approach for mitigating domain shift in medical image segmentation; however, current evaluations remain limited in terms of modality coverage, task diversity, and methodological consistency. We present…
Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…
With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile…
The evolution toward 6G networks demands a fundamental shift from bit-centric transmission to semantic-aware communication that emphasizes task-relevant information. This work introduces TOAST (Task-Oriented Adaptive Semantic Transmission),…
Test-time adaptation (TTA) has demonstrated significant potential in addressing distribution shifts between training and testing data. Open-set test-time adaptation (OSTTA) aims to adapt a source pre-trained model online to an unlabeled…
Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence…