Analyzing high-dimensional data presents challenges due to the "curse of dimensionality'', making computations intensive. Dimension reduction techniques, categorized as linear or non-linear, simplify such data. Non-linear methods are particularly essential for efficiently visualizing and processing complex data structures in interactive and graphical applications. This research develops an incremental non-linear dimension reduction method using the Geometric Multi-Resolution Analysis (GMRA) framework for streaming data. The proposed method enables real-time data analysis and visualization by incrementally updating the cluster map, PCA basis vectors, and wavelet coefficients. Numerical experiments show that the incremental GMRA accurately represents non-linear manifolds even with small initial samples and aligns closely with batch GMRA, demonstrating efficient updates and maintaining the multiscale structure. The findings highlight the potential of Incremental GMRA for real-time visualization and interactive graphics applications that require adaptive high-dimensional data representations.

This pilot study presents a novel, automated, and scalable methodology for detecting and evaluating subsurface defect-prone regions in concrete slabs using Impact Echo (IE) signal analysis. The approach integrates advanced signal processing, clustering, and visual analytics to identify subsurface anomalies. A unique adaptive thresholding method tailors frequency-based defect identification to the distinct material properties of each slab. The methodology generates frequency maps, binary masks, and k-means cluster maps to automatically classify defect and non-defect regions. Key visualizations, including 3D surface plots, cluster maps, and contour plots, are employed to analyze spatial frequency distributions and highlight structural anomalies. The study utilizes a labeled dataset constructed at the Federal Highway Administration (FHWA) Advanced Sensing Technology Nondestructive Evaluation Laboratory. Evaluations involve ground-truth masking, comparing the generated defect maps with top-view binary masks derived from the information provided by the FHWA. The performance metrics, specifically F1-scores and AUC-ROC, achieve values of up to 0.95 and 0.83, respectively. The results demonstrate the robustness of the methodology, consistently identifying defect-prone areas with minimal false positives and few missed defects. Adaptive frequency thresholding ensures flexibility in addressing variations across slabs, providing a scalable framework for detecting structural anomalies. Additionally, the methodology is adaptable to other frequency-based signals due to its generalizable thresholding mechanism and holds potential for integrating multimodal sensor fusion. This automated and scalable pipeline minimizes manual intervention, ensuring accurate and efficient defect detection, further advancing Non-Destructive Evaluation (NDE) techniques.

We propose sorting patch representations across views as a novel self-supervised learning signal to improve pretrained representations. To this end, we introduce NeCo: Patch Neighbor Consistency, a novel training loss that enforces patch-level nearest neighbor consistency across a student and teacher model, relative to reference batches. Our method leverages a differentiable sorting method applied on top of pretrained representations, such as DINOv2-registers to bootstrap the learning signal and further improve upon them. This dense post-pretraining leads to superior performance across various models and datasets, despite requiring only 19 hours on a single GPU. We demonstrate that this method generates high-quality dense feature encoders and establish several new state-of-the-art results: +5.5% and + 6% for non-parametric in-context semantic segmentation on ADE20k and Pascal VOC, and +7.2% and +5.7% for linear segmentation evaluations on COCO-Things and -Stuff.

Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific class is identified, without providing a detailed explanation of the model's decision process. Striving to address such a need, we introduce a post-hoc method that explains the entire feature extraction process of a Convolutional Neural Network. These explanations include a layer-wise representation of the features the model extracts from the input. Such features are represented as saliency maps generated by clustering and merging similar feature maps, to which we associate a weight derived by generalizing Grad-CAM for the proposed methodology. To further enhance these explanations, we include a set of textual labels collected through a gamified crowdsourcing activity and processed using NLP techniques and Sentence-BERT. Finally, we show an approach to generate global explanations by aggregating labels across multiple images.

Reflectance Confocal Microscopy (RCM) marks a paradigm shift in biomedical imaging, offering a sophisticated, non-invasive technique to acquire high-resolution images of the skin and superficial tissues. Its development [1] represents a milestone in medical imaging, transitioning from early exploratory stages to becoming a cornerstone in clinical dermatology. RCM's capability for in vivo imaging, capturing live tissue images without the need for biopsies or tissue excision, has made it an indispensable tool in modern medical diagnostics. The inception of RCM can be traced back to its early conceptualization, where the need for less invasive, more accurate diagnostic methods in dermatology was recognized. Over the years, the technology has undergone significant advancements, evolving in its design and functionality. This evolution has been marked by improvements in laser source quality, detector sensitivity, and image processing algorithms, resulting in enhanced image clarity and depth of tissue analysis. RCM's operation relies on a focused laser light to illuminate the target tissue. The tissue interaction with this light, primarily through backscattering and reflection, forms the basis of image creation.

Manually sifting through 1,000 images is tricky, but what about 1,000,000? What if we get a new batch of 10,000 images every day? Many who work on various computer vision tasks face a similar challenge. Akridata Data Explorer is a unique and powerful tool for data curation. Curating and exploring your database is the first step to having a clean database, which can be used for model training and testing.

The quality of a good sleep is important for a healthy life. Recently, several sleep analysis products have emerged on the market; however, many of them require additional hardware or there is a lack of scientific evidence regarding their clinical efficacy. We proposed a novel method via clustering of sound events for discovering the sleep pattern. This method extended conventional self-organizing map algorithm by kernelized and sequence-based technologies, obtained a fine-grained map that depicts the distribution and changes of sleep-related events. We introduced widely applied features in sound processing and popular kernel functions to our method, evaluated their performance, and made a comparison. Our method requires few additional hardware, and by visualizing the transition of cluster dynamics, the correlation between sleep-related sound events and sleep stages was revealed.