Nondestructive detection methods based on vibrational spectroscopy have been widely used in many critical applications in a variety of fields such as the chemical industry, pharmacy, national defense, security, and so on. As these methods/applications rely on machine learning models for data analysis, studying the threats associated with adversarial examples in vibrational spectroscopy and defenses against them is of great importance. In this paper, we propose a novel adversarial method to attack vibrational spectroscopy, named SynPat, where synthetic peaks produced by a physical model are placed at key locations to form adversarial perturbations.
View Article and Find Full Text PDFIEEE Trans Image Process
January 2024
Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap include reducing the distributional differences of representations of different modalities, learning indistinguishable representations or explicit modality transfer. The first two approaches suffer from the loss of discriminant information while removing the modality-specific variations.
View Article and Find Full Text PDFIEEE Trans Pattern Anal Mach Intell
May 2024
Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistry, pharmacy and national defense. Recently, deep learning has been introduced into vibrational spectroscopy showing great potential. Different from images, text, etc.
View Article and Find Full Text PDFAtomic-scale features, such as step edges and adatoms, play key roles in metal-molecule interactions and are critically important in heterogeneous catalysis, molecular electronics, and sensing applications. However, the small size and often transient nature of atomic-scale structures make studying such interactions challenging. Here, by combining single-molecule surface-enhanced Raman spectroscopy with machine learning, spectra are extracted of perturbed molecules, revealing the formation dynamics of adatoms in gold and palladium metal surfaces.
View Article and Find Full Text PDFOne of the most-extensively studied problems in three-dimensional Computer Vision is "Perspective-n-Point" (PnP), which concerns estimating the pose of a calibrated camera, given a set of 3D points in the world and their corresponding 2D projections in an image captured by the camera. One solution method that ranks as very accurate and robust proceeds by reducing PnP to the minimization of a fourth-degree polynomial over the three-dimensional sphere S3. Despite a great deal of effort, there is no known fast method to obtain this goal.
View Article and Find Full Text PDFCoreset of a given dataset and loss function is usually a small weighed set that approximates this loss for every query from a given set of queries. Coresets have shown to be very useful in many applications. However, coresets' construction is done in a problem-dependent manner and it could take years to design and prove the correctness of a coreset for a specific family of queries.
View Article and Find Full Text PDFDeep neural networks (DNNs) models have the potential to provide new insights in the study of cognitive processes, such as human decision making, due to their high capacity and data-driven design. While these models may be able to go beyond theory-driven models in predicting human behaviour, their opaque nature limits their ability to explain how an operation is carried out, undermining their usefulness as a scientific tool. Here we suggest the use of a DNN model as an exploratory tool to identify predictable and consistent human behaviour, and using explicit, theory-driven models, to characterise the high-capacity model.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
December 2022
Model compression is crucial for the deployment of neural networks on devices with limited computational and memory resources. Many different methods show comparable accuracy of the compressed model and similar compression rates. However, the majority of the compression methods are based on heuristics and offer no worst case guarantees on the tradeoff between the compression rate and the approximation error for an arbitrarily new sample.
View Article and Find Full Text PDFThe deep learning revolution introduced a new and efficacious way to address computational challenges in a wide range of fields, relying on large data sets and powerful computational resources. In protein engineering, we consider the challenge of computationally predicting properties of a protein and designing sequences with these properties. Indeed, accurate and fast deep network oracles for different properties of proteins have been developed.
View Article and Find Full Text PDFMachine learning methods have found many applications in Raman spectroscopy, especially for the identification of chemical species. However, almost all of these methods require non-trivial preprocessing such as baseline correction and/or PCA as an essential step. Here we describe our unified solution for the identification of chemical species in which a convolutional neural network is trained to automatically identify substances according to their Raman spectrum without the need for preprocessing.
View Article and Find Full Text PDFA canonical problem in computer vision is category recognition (e.g., find all instances of human faces, cars etc.
View Article and Find Full Text PDFWe present a novel approach to pose estimation and model-based recognition of specular objects in difficult viewing conditions, such as low illumination, cluttered background, large highlights, and shadows that appear on the object of interest. In such challenging conditions, conventional features are unreliable. We show that under the assumption of a dominant light source, specular highlights produced by a known object can be used to establish correspondence between its image and the 3D model, and to verify the hypothesized pose and the identity of the object.
View Article and Find Full Text PDFProc Natl Acad Sci U S A
July 2011
To study the protein structure-function relationship, we propose a method to efficiently create three-dimensional maps of structure space using a very large dataset of > 30,000 Structural Classification of Proteins (SCOP) domains. In our maps, each domain is represented by a point, and the distance between any two points approximates the structural distance between their corresponding domains. We use these maps to study the spatial distributions of properties of proteins, and in particular those of local vicinities in structure space such as structural density and functional diversity.
View Article and Find Full Text PDFIEEE Trans Pattern Anal Mach Intell
January 2007
We consider the problem of matching images to tell whether they come from the same scene viewed under different lighting conditions. We show that the surface characteristics determine the type of image comparison method that should be used. Previous work has shown the effectiveness of comparing the image gradient direction for surfaces with material properties that change rapidly in one direction.
View Article and Find Full Text PDF