Related papers: Analysis of Classifier Training on Synthetic Data …

Deep learning models for self-driving cars require a diverse training dataset to manage critical driving scenarios on public roads safely. This includes having data from divergent trajectories, such as the oncoming traffic lane or…

The integration of machine learning (ML) models enhances the efficiency, affordability, and reliability of feature detection in microscopy, yet their development and applicability are hindered by the dependency on scarce and often flawed…

Automated tuning of gate-defined quantum dots is a requirement for large scale semiconductor based qubit initialisation. An essential step of these tuning procedures is charge state detection based on charge stability diagrams. Using…

Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep…

Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…

Traffic light recognition, as a critical component of the perception module of self-driving vehicles, plays a vital role in the intelligent transportation systems. The prevalent deep learning based traffic light recognition methods heavily…

Deep reinforcement learning (DRL) demonstrates its potential in learning a model-free navigation policy for robot visual navigation. However, the data-demanding algorithm relies on a large number of navigation trajectories in training.…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

The development in the field of autonomous driving goes hand in hand with ever new developments in the field of image processing and machine learning methods. In order to fully exploit the advantages of deep learning, it is necessary to…

Artificial intelligence (AI), machine learning, and deep learning (DL) methods are becoming increasingly important in the field of biomedical image analysis. However, to exploit the full potential of such methods, a representative number of…

Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock…

Learning robust object detectors from only a handful of images is a critical challenge in industrial vision systems, where collecting high quality training data can take months. Synthetic data has emerged as a key solution for data…

The performance of supervised deep learning algorithms depends significantly on the scale, quality and diversity of the data used for their training. Collecting and manually annotating large amount of data can be both time-consuming and…

Are general-purpose visual representations acquired solely from synthetic data useful for detecting fake images? In this work, we show the effectiveness of synthetic data-driven representations for synthetic image detection. Upon analysis,…

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vision tasks. The main contribution is a procedural world…

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This…

Although there are many datasets for traffic sign classification, there are few datasets collected for traffic sign recognition and few of them obtain enough instances especially for training a model with the deep learning method. The deep…