Related papers: Spectrum Translation for Cross-Spectral Ocular Mat…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
Ultrasound simulation based on ray tracing enables the synthesis of highly realistic images. It can provide an interactive environment for training sonographers as an educational tool. However, due to high computational demand, there is a…
We present the Hue-Net - a novel Deep Learning framework for Intensity-based Image-to-Image Translation. The key idea is a new technique termed network augmentation which allows a differentiable construction of intensity histograms from…
Hyperspectral imaging captures both spectral and spatial information from a sample. The near infrared (NIR, > 800 nm) is advantageous for biomedical imaging as it falls into the tissue transparency window but also contains vibrational…
Hyperspectral imaging (HSI) unlocks the huge potential to a wide variety of applications relied on high-precision pathology image segmentation, such as computational pathology and precision medicine. Since hyperspectral pathology images…
Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition. In this work, we adapt a ViT model pretrained on visible (VIS) imagery to the challenging…
Purpose: Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral…
This article addresses the problem of two- and higher dimensional pattern matching, i.e. the identification of instances of a template within a larger signal space, which is a form of registration. Unlike traditional correlation, we aim at…
Binary-source code matching plays an important role in many security and software engineering related tasks such as malware detection, reverse engineering and vulnerability assessment. Currently, several approaches have been proposed for…
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data. By utilizing CNN in extracting local semantics, various techniques have been developed to improve the…
Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models focus on parsing the high-resolution and clean images. However, directly applying the parsers…
Synthetic Aperture Radar (SAR) imaging technology provides the unique advantage of being able to collect data regardless of weather conditions and time. However, SAR images exhibit complex backscatter patterns and speckle noise, which…
Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…
Cross-modal representation learning learns a shared embedding between two or more modalities to improve performance in a given task compared to using only one of the modalities. Cross-modal representation learning from different data types…
Deep learning has thrived by training on large-scale datasets. However, in many applications, as for medical image diagnosis, getting massive amount of data is still prohibitive due to privacy, lack of acquisition homogeneity and annotation…
Direct image-to-graph transformation is a challenging task that involves solving object detection and relationship prediction in a single model. Due to this task's complexity, large training datasets are rare in many domains, making the…
Purpose: A major barrier to the implementation of artificial intelligence for medical applications is the lack of explainability and high confidence for incorrect decisions, specifically with out-of-domain samples. We propose a…
Face signatures, including size, shape, texture, skin tone, eye color, appearance, and scars/marks, are widely used as discriminative, biometric information for access control. Despite recent advancements in facial recognition systems,…
Hypernetworks are models that generate or modulate the weights of another network. They provide a flexible mechanism for injecting context and task conditioning and have proven broadly useful across diverse applications without significant…
Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a…