Related papers: A Data-Driven Novelty Score for Diverse In-Vehicle…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

Machine learning has emerged as a promising paradigm for enabling connected, automated vehicles to autonomously cruise the streets and react to unexpected situations. A key challenge, however, is to collect and select real-time and reliable…

Data imbalance is a well-known issue in the field of machine learning, attributable to the cost of data collection, the difficulty of labeling, and the geographical distribution of the data. In computer vision, bias in data distribution…

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method…

Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting…

Recent efforts towards video anomaly detection (VAD) try to learn a deep autoencoder to describe normal event patterns with small reconstruction errors. The video inputs with large reconstruction errors are regarded as anomalies at the test…

Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed…

This paper introduces a novel anomaly detection framework that combines the robust statistical principles of density-estimation-based anomaly detection methods with the representation-learning capabilities of deep learning models. The…

Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of…

Regression testing in software development checks if new software features affect existing ones. Regression testing is a key task in continuous development and integration, where software is built in small increments and new features are…

Large high-dimensional datasets are becoming more and more popular in an increasing number of research areas. Processing the high dimensional data incurs a high computational cost and is inherently inefficient since many of the values that…

Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…

When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks, a critical failure known as catastrophic forgetting. This challenge severely limits the deployment of AI in…

We aim for image-based novelty detection. Despite considerable progress, existing models either fail or face a dramatic drop under the so-called "near-distribution" setting, where the differences between normal and anomalous samples are…

Deep learning has enabled various Internet of Things (IoT) applications. Still, designing models with high accuracy and computational efficiency remains a significant challenge, especially in real-time video processing applications. Such…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

In dynamic environments, the ability to detect and track moving objects in real-time is crucial for autonomous robots to navigate safely and effectively. Traditional methods for dynamic object detection rely on high accuracy odometry and…

Deep neural networks (DNN) which are employed in perception systems for autonomous driving require a huge amount of data to train on, as they must reliably achieve high performance in all kinds of situations. However, these DNN are usually…

We introduce a novel tracking technique which uses dynamic confidence-based fusion of two different information sources for robust and efficient tracking of visual objects. Mean-shift tracking is a popular and well known method used in…

Novelty detection in news events has long been a difficult problem. A number of models performed well on specific data streams but certain issues are far from being solved, particularly in large data streams from the WWW where…