Related papers: Test Time Adaptation for Blind Image Quality Asses…

Deep classifiers may encounter significant performance degradation when processing unseen testing data from varying centers, vendors, and protocols. Ensuring the robustness of deep models against these domain shifts is crucial for their…

Ensemble methods improve predictive performance but often incur high memory and computational costs. We identify an aggregation instability induced by nonlinear projection and voting operations. To address both efficiency challenges and…

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification…

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…

Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for…

Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions. However, these attempts may fail under more challenging real-world scenarios. Existing…

Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images. Similarly, BIQA models optimized for images…

Test-time adaptation aims to adapt pre-trained deep neural networks using solely online unlabelled test data during inference. Although TTA has shown promise in visual applications, its potential in time series contexts remains largely…

Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under \textit{temporally evolving distribution shifts} common in real-world scenarios (e.g., gradual illumination or seasonal…

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially, TTA assumes no access to the source data or even any…

Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation (TTA) emerges as a predominant strategy to adapt VLMs to unlabeled test data on the fly. However,…

Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples. This flexibility suits real deployments, yet…

Test-time augmentation (TTA)--aggregating predictions over multiple augmented copies of a test input--is widely assumed to improve classification accuracy, particularly in medical imaging where it is routinely deployed in production systems…

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…

Test-time adaptation (TTA) aims to adapt a pretrained model to distribution shifts using only unlabeled test data. While promising, existing methods like Tent suffer from instability and can catastrophically forget the source knowledge,…

In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a…

The performance of many medical image analysis tasks are strongly associated with image data quality. When developing modern deep learning algorithms, rather than relying on subjective (human-based) image quality assessment (IQA), task…

Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external…