A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CViT learns complex physical systems using vision transformer techniques.
The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accepted in the competition track of 32nd Conference on Neural In…
The growing role that artificial intelligence and specifically machine learning is playing in shaping the future of wireless communications has opened up many new and intriguing research directions. This paper motivates the research in the novel direction of \textit{vision-aided wireless communications}, which aims at …
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This grou…
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clo…
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
Survey of complex-valued neural networks for improved performance.
Active learning improves inspection systems by using weakly labeled data.
Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored lar…
B-cos transformers explain Vision Transformers' decisions.
Scoping review of EO-ML methods for causal inference in poverty geography.
TACTO simulates high-resolution touch sensing for robotics.
With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision problems are still solved by different models, trained from scratch or fine-tuned o…
Framework for efficient defect classification and inspection.
Develops methods for training models with few annotations in computer vision tasks.
While frame-independent predictions with deep neural networks have become the prominent solutions to many computer vision tasks, the potential benefits of utilizing correlations between frames have received less attention. Even though probabilistic machine learning provides the ability to encode correlation as prior kn…
Machine vision is critical to robotics due to a wide range of applications which rely on input from visual sensors such as autonomous mobile robots and smart production systems. To create the smart homes and systems of tomorrow, an overview about current challenges in the research field would be of use to identify furt…
A machine learning method predicts rock permeability from 3D images.
V-HMN integrates memory mechanisms for improved image recognition.
New methods adapt conformal prediction to unknown subpopulation shifts.
Explains equivariant neural networks for machine learning.
This paper surveys algorithmic advancements in Optimal Transport with applications in machine learning.
Machine learning has evolved into an enabling technology for a wide range of highly successful applications. The potential for this success to continue and accelerate has placed machine learning (ML) at the top of research, economic and political agendas. Such unprecedented interest is fuelled by a vision of ML applica…
Deep learning improves material recognition in construction monitoring.
This dissertation tackles challenges in reliable machine learning measurement.
Novel approach to contextual bandits using self-supervised learning.
Improved model robustness against corruptions using online adaptation.
This paper reviews and proposes a unified framework for contrastive learning.
This study automates blood cell classification using computer vision.
GWHD dataset offers 4,700 high-res images of wheat heads.
Article presents QR and LQ decomposition algorithms for various matrix sizes and ranks.
Evaluates deep learning models in histopathology for robustness and classification strategies.
Extracts factors from Treasury yields using ML techniques.
Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning…
New mechanism discovered for feature learning in CNNs.
New methods for graph completion improve image annotation and neuroimaging.
Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions. The recent developments on alternative formulations of the optimal transport have allowed for faster solutio…
Sparse Vision MoE matches dense networks in image recognition while using less compute.
MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this …
We present an exploration of the rich theoretical connections between several classes of regularized models, network flows, and recent results in submodular function theory. This work unifies key aspects of these problems under a common theory, leading to novel methods for working with several important models of inter…
Robust CLIP improves vision models' resistance to attacks.
Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision. Using a large amount of unlabeled data, unsupervised feature learning methods are utilized to construct high-level representations that are discriminative en…
We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demo…
Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, ignoring the interactions between predictions of future moments with different temporal distance. Such a deficiency probably prevents the model …
We propose to apply deep transfer learning from computer vision to static malware classification. In the transfer learning scheme, we borrow knowledge from natural images or objects and apply to the target domain of static malware detection. As a result, training time of deep neural networks is accelerated while high c…
This paper studies the application of machine learning in extracting the market implied features from historical risk neutral corporate bond yields. We consider the example of a hypothetical illiquid fixed income market. After choosing a surrogate liquid market, we apply the Denoising Autoencoder algorithm from the fie…