Related papers: Raman spectroscopy in open world learning settings…

Convolutional neural networks (CNN) have been shown to provide a good solution for classification problems that utilize data obtained from vibrational spectroscopy. Moreover, CNNs are capable of identification from noisy spectra without the…

Often, when dealing with real-world recognition problems, we do not need, and often cannot have, knowledge of the entire set of possible classes that might appear during operational testing. In such cases, we need to think of robust…

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{right to be forgotten} emphasized by…

Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often…

In general, most of the substances in nature exist in mixtures, and the noninvasive identification of mixture composition with high speed and accuracy remains a difficult task. However, the development of Raman spectroscopy, machine…

Raman micro/macro-spectroscopy allows for a non-destructive remote analysis: body and glaze, crystalline and amorphous phases can be identified, including the nanosized pigments colouring the glaze. Last generation instruments are portable…

The reliance on Deep Neural Network (DNN)-based classifiers in safety-critical and real-world applications necessitates Open-Set Recognition (OSR). OSR enables the identification of input data from classes unknown during training as…

We introduce a machine learning prediction workflow to study the impact of defects on the Raman response of 2D materials. By combining the use of machine-learned interatomic potentials, the Raman-active $\Gamma$-weighted density of states…

Open-World Recognition (OWR) is an emerging field that makes a machine learning model competent in rejecting the unknowns, managing them, and incrementally adding novel samples to the base knowledge. However, this broad objective is not…

Optical coherence tomography (OCT) scanning is useful in detecting various retinal diseases. However, there are not enough ophthalmologists who can diagnose retinal OCT images in much of the world. To provide OCT screening inexpensively and…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

Interpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand their surroundings and need the ability to deal with novel…

We investigate the problem of Object State Classification (OSC) as a zero-shot learning problem. Specifically, we propose the first Object-agnostic State Classification (OaSC) method that infers the state of a certain object without relying…

A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds…

Open Set Recognition (OSR) extends image classification to an open-world setting, by simultaneously classifying known classes and identifying unknown ones. While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they…

Raman spectroscopy has attracted interest as a non-invasive optical technique to study the composition and structure of a wide range of materials at the microscopic level. The intrinsic fluorescence background can be orders of magnitude…

Open World Object Detection(OWOD) addresses realistic scenarios where unseen object classes emerge, enabling detectors trained on known classes to detect unknown objects and incrementally incorporate the knowledge they provide. While…

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

Surface enhanced Raman spectroscopy, is a technique of fundamental importance to analytical science and technology where the amplified Raman spectrum of analytes is used for chemical fingerprinting. Here, we showcase an engineered…

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes…