Related papers: Orochi: Versatile Biomedical Image Processor
The rapid evolution of deep learning has significantly advanced the field of medical image analysis. However, despite these achievements, the further enhancement of deep learning models for medical image analysis faces a significant…
Optical multilayer thin-films are fundamental components that enable the precise control of reflectance, transmittance, and phase shift in the design of photonic systems. Rapid and accessible simulation of these structures holds critical…
We investigate how both the adaptation of a generic foundation model via transfer learning and the integration of complementary modalities from the operating room (OR) can support surgical data science. To this end, we use V-JEPA as the…
A variety of complicated computational scenarios have made unprecedented demands on the computing power and energy efficiency of electronic computing systems, including solving intractable nondeterministic polynomial-time (NP)-complete…
In biomedical imaging, deep learning-based methods are state-of-the-art for every modality (virtual slides, MRI, etc.) In histopathology, these methods can be used to detect certain biomarkers or classify lesions. However, such techniques…
Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks.…
Oculomics - the concept of predicting systemic diseases, such as cardiovascular disease and dementia, through retinal imaging - has advanced rapidly due to the data efficiency of transformer-based foundation models like RETFound.…
The rapid advancement of image analysis methods in time-domain astronomy, particularly those leveraging AI algorithms, has highlighted efficient image pre-processing as a critical bottleneck affecting algorithm performance. Image…
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…
Deep neural networks (DNNs) are reshaping the field of information processing. With their exponential growth challenging existing electronic hardware, optical neural networks (ONNs) are emerging to process DNN tasks in the optical domain…
There has been much progress in data-driven artificial intelligence technology for medical image analysis in the last decades. However, it still remains challenging due to its distinctive complexity of acquiring and annotating image data,…
Prevention and early diagnosis of breast cancer (BC) is an essential prerequisite for the selection of proper treatment. The substantial pressure due to the increase of demand for faster and more precise diagnostic results drives for…
Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…
Recent advances in self-supervised learning for Vision Transformers (ViTs) have fueled breakthroughs in remote sensing (RS) foundation models. However, the quadratic complexity of self-attention poses a significant barrier to scalability,…
Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade…
Curating, processing, and combining large-scale medical imaging datasets from national studies is a non-trivial task due to the intense computation and data throughput required, variability of acquired data, and associated financial…
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…
The combination of transformers and masked image modeling (MIM) pre-training framework has shown great potential in various vision tasks. However, the pre-training computational budget is too heavy and withholds the MIM from becoming a…
Deep optics has emerged as a promising approach by co-designing optical elements with deep learning algorithms. However, current research typically overlooks the analysis and optimization of manufacturing and assembly tolerances. This…
Advanced photonic tools may enable researchers and clinicians to visualize, track, control and manipulate biological processes at the single-cell level in space and time. Biological systems are complex and highly organized on both spatial…