1,720,963 research outputs found
Adaptive Test-Time Learning Under Domain Shift: From Augmentation to Prolonged Adaptation
No full textDeep neural networks often fail to generalize when deployed in dynamic and unpredictable real-world environments, where data distributions at test time can differ significantly from those encountered during training. Since simulating all possible distribution shifts during supervised training is computationally impractical, this dissertation investigates how to adapt vision-based models at inference time, without requiring labeled test data or access to the original training set, within the paradigm of source-free test-time learning.
The thesis first explores test-time adaptation of inputs rather than models. For vision tasks like MRI segmentation with contrast-based domain shifts, we show targeted image transformations effectively reduce training-test distribution gaps. Our approach learns image augmentations via unsupervised loss functions to simulate training image styles without accessing the original dataset. This gradient-driven method improves performance when input alignment is critical but parameter updates are impractical. However, for real-world deployment with continuously evolving data distributions, dynamic test-time adaptation offers a more robust solution by actively adjusting model parameters to changing conditions.
Extending this idea, the thesis develops a self-distillation framework that tackles more complex domain shifts that simple image transformations alone cannot resolve, such as staining differences in histopathology or lighting variations in outdoor scene segmentation. By strategically crafting adversarial augmentations that exaggerate domain shifts, the model is trained to remain consistent through pseudo-label supervision provided by a corresponding mean teacher model. This results in significantly enhanced robustness under severe distributional changes, enabling reliable performance in more challenging
real-world scenarios.
Nonetheless, most existing test-time adaptation methods fail in realistic deployment settings where the data distribution evolves gradually and samples exhibit temporal correlations. To address this, the thesis introduces a novel test-time normalization recalibration strategy. By disentangling and dynamically updating skewed batch statistics through an online unmixing mechanism, our method effectively tracks evolving data distributions using a similarity-based clustering of incoming test instances. This leads to more stable and reliable model adaptation over time, particularly in environments where the test data is sampled correlatively and conditions shift progressively.
Finally, the thesis presents a plug-in framework for prolonged test-time learning in continuously evolving environments. Unlike conventional single-model approaches that suffer from catastrophic forgetting and inter-domain interference, our framework employs adaptive online clustering based on domain style features to detect and track evolving target domains, enabling domain-specific adaptation.
These contributions significantly advance source-free test-time adaptation in computer vision by addressing critical challenges in domain generalization, calibration, and robustness. Our methods achieve state-of-the-art performance across multiple benchmarks and establish a practical foundation for deploying deep learning models in real-world, continuously evolving conditions, particularly in safety-critical applications where reliable predictions are essential despite changing environments.LTS
Sagtta: saliency guided test time augmentation for medical image segmentation across vendor domain shift
No full textTest time augmentation has been shown to be an effective approach to combat domain shifts in deep learning. Despite their promising performance levels, the interpretability of the underlying used models is however low. Saliency maps have been widely used in medical image analysis as a post-hoc interpretability method for deep learning models. Beyond explainability, in this study, we propose SaGTTA (Saliency Guided Test Time Augmentation), the first learnable framework that introduces saliency information to guide test time augmentations via a novel self-supervised loss term. During test time augmentation, the proposed self-supervised saliency-guided loss aims at promoting augmentation policies that enhance the distinctiveness among class-specific saliency maps. By promoting saliency distinctiveness among different labels of the test image during test time augmentation, the data distribution discrepancy between the test image and training dataset is alleviated. We compared the proposed method with a state-of-the-art method, using a publicly available dataset, showing improvements in terms of performance, model calibration, and robustness. The code will be made publicly available at https://github.com/yousuhang/SaGTTA.LTS
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
Author-wise bibliometric analysis based on entropy.
No full textAuthor-wise bibliometric analysis based on entropy.</p
- …
