23 papers · ranked by Valyu relevance
Benjamin Sanders, David Morrison, David Harris-Birtill, Luca Citi
The recent development of text-to-image diffusion models has allowed us to quickly generate realistic images from textual prompts. Despite enabling innovation in particular domains, concerns have been raised over the prospect of malicious users posing synthetic images as genuine. To assess if it is possible to discern…
Neelanjan Ghosh, Gouranga Mandal
Image colorization transforms grayscale images into realistic color representations. It is a challenging area of research in computer vision due to uncertainty in mapping intensity values to chromatic information. Earlier approaches, often based on optimization or reference-guided strategies, depend extensively on…
Matéo Mahaut, Marco Baroni
Recent literature suggests that the bigger the model, the more likely it is to converge to similar, "universal" representations, despite different training objectives, datasets, or modalities. While this literature shows that there is an area where model representations are similar, we study here how vision models…
Soroush Ziaee, Ram Ahuja, Sabine Muzellec, Ezgi Fide + 2 more
The primate inferior temporal (IT) cortex, at the apex of the ventral visual stream, encodes information that supports diverse representational goals—from recognizing objects to determining which images are likely to be remembered. Specific artificial neural networks (ANNs), that currently serve as the leading…
Yu (Eric) Qian, Wilson S. Geisler, Xue-Xin Wei
Previous studies have compared neural activities in the visual cortex to representations in deep neural networks trained on image classification. Interestingly, while some suggest that their representations are highly similar, others argued the opposite. Here, we propose a new approach to characterize the similarity of…
Mian Usman Sattar, Meznah A. Alamro, Alaeddine Mihoub, Soliman Aljarboa + 1 more
Introduction Computed Tomography (CT) brain scans are crucial for diagnosing various neurological conditions, including tumors, cancer, and aneurysms. CT brain scans are essential for guiding treatment decisions and monitoring disease progression. In this study, we propose a novel framework for brain CT image…
K. E. ArunKumar, Matthew E. Wilson, Nathan E. Blake, Tylor J. Yost + 3 more
Early detection of breast cancer commonly relies on imaging technologies such as ultrasound, mammography and MRI. Among these, breast ultrasound is widely used by radiologists to identify and assess lesions. In this study, we developed image segmentation techniques and multiclass classification artificial intelligence…
Niall Rodgers
Palaeontology has seen widespread and growing use of machine learning to classify and analyse large datasets of fossils. However, palaeontology is a challenging field in which to apply machine learning. Datasets may be small or unlabelled, images may be complex and different from standard datasets and palaeontologists…
Neetu Agrawal, Mehul Mahrishi, Mukesh Kumar Gupta, Manoj Kumar Bohra
The United Nations’ Sustainable Development Goals, SDG 12: Responsible Consumption and Production, and SDG 13: Climate Action highlight the importance of environmental conservation and reducing pesticide use. Early and accurate pest identification is essential for implementing targeted pest control measures, which…
Authors not listed
Infrared (IR) spectroscopy provides rich structural information but interpreting spectra at scale remains challenging. Here we introduce j-IR-vis, a vision-based neural model that learns chemically interpretable representations directly from IR spectra for functional-group prediction and downstream molecular…
Chloe A. Game, Nils Piechaud, Kerry L. Howell
Deep learning (DL) is a powerful tool to extract ecological information from large image datasets efficiently and consistently. However, applying these methods remains challenging, due in part to the complexity of DL workflows and the dynamic nature of available tools. To address this, we created a practical guide and…
Erukude, Sai Teja
Convolutional Neural Networks are now prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of userfriendly libraries. These networks effortlessly identify and select features in a non-intuitive data-driven manner, making it difficult to…
Aashish Dhawan, Divyanshu Mudgal
— the major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can overcome the scarcity of data to produce results comparable to previous benchmark…
Ethan Chung, Chuanjun Zheng, Jasper Tan, Jingxi Li + 2 more
Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks, but it remains unclear whether they can handle the physics and inverse problems that underlie computational imaging. We present ImagingBench, a benchmark of 20 computational imaging tasks spanning five categories: ray…
Tahsin Islam. Sakif, Nasser Nasrabadi, Jeremy Dawson
Large-scale biometric systems, essential for national security and border management, increasingly rely on multimodal databases containing millions of identities. However, operational pressures and insufficient training lead to frequent image classification and labeling errors by human operators. These critical data…
Yuanhao Gong, Tan Tang, Qianyan Liu
The Laplacian operator transforms the image into its Laplacian field, which usually is sparse and satisfies a stable distribution. On the other hand, an image can be uniquely reconstructed from its Laplacian field via solving a Poisson equation with a proper boundary condition. Such uniqueness is mathematically…
Ruoyu Feng, Yunpeng Qi, Jinming Liu, Yixin Gao + 4 more
Image compression methods are usually optimized isolatedly for human perception or machine analysis tasks. We reveal fundamental commonalities between these objectives: preserving accurate semantic information is paramount, as it directly dictates the integrity of critical information for intelligent tasks and aids…
Sreenivas Bhattiprolu, Manita Toor, Sebastian Soyer
Modern biological imaging generates large, complex datasets that require scalable and reproducible image analysis methods. Deep learning has demonstrated strong performance on bioimage segmentation tasks, but training custom models has remained inaccessible to many researchers due to requirements for GPU…
Yifan Luo, Niklas Müller, H. Steven Scholte
Deep convolutional neural networks match human accuracy on standard object recognition tasks but fail to recognize familiar objects from novel view-points. Humans, however, develop viewpoint-invariant recognition at an early age through diverse visual experience. This gap in visual experience may explain why models…
Omveer Sharma, Keren Weidenfeld, Dalit Barkan, Oren Gal
Breast cancer cells that disseminate to distant organs can remain dormant (non-proliferative) for years before reactivating and progressing into lethal metastatic disease. Understanding the transition between dormancy and reactivation is therefore critical for early intervention and treatment. In this study, we…
Authors not listed
The ability to track therapeutic cells is critical for advancing adoptive cell therapy (ACT). Positron emission tomography (PET) offers sensitive and quantitative imaging, yet improved cell radiolabeling strategies are sorely needed. We report a metabolic glycoengineering (MGE) approach that installs azide moieties on…
Authors not listed
Olfaction arises from the interaction of odorants with olfactory receptors, a process shaped by molecular geometry, electron distribution, and conformational preference. We present ConfDENSE, a Set2Set enhanced PointNet model that learns directly from Hirshfeld promolecule electron-density point clouds, preserving full…
Vittorio Palladino, Ahmet Enis Cetin
Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep learning approaches have achieved promising results on static scenes, two critical limitations remain unaddressed: existing architectures fail…