相关论文: Domain Randomization for Object Counting

Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the…

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data,…

We propose a new method to count objects of specific categories that are significantly smaller than the ground sampling distance of a satellite image. This task is hard due to the cluttered nature of scenes where different object categories…

This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings…

Synthetic data is an increasingly popular tool for training deep learning models, especially in computer vision but also in other areas. In this work, we attempt to provide a comprehensive survey of the various directions in the development…

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance.…

This paper addresses the synthetic-to-real domain gap in object detection, focusing on training a YOLOv11 model to detect a specific object (a soup can) using only synthetic data and domain randomization strategies. The methodology involves…

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…

In recent years, image manipulation is becoming increasingly more accessible, yielding more natural-looking images, owing to the modern tools in image processing and computer vision techniques. The task of the identification of forged…

The size of large, geo-located datasets has reached scales where visualization of all data points is inefficient. Random sampling is a method to reduce the size of a dataset, yet it can introduce unwanted errors. We describe a method for…

Data simulation engines like Unity are becoming an increasingly important data source that allows us to acquire ground truth labels conveniently. Moreover, we can flexibly edit the content of an image in the engine, such as objects…

Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated…

Accurate product information is critical for e-commerce stores to allow customers to browse, filter, and search for products. Product data quality is affected by missing or incorrect information resulting in poor customer experience. While…

Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learning. In this work, we focus on autoencoder architectures and…

Cross-domain synthesizing realistic faces to learn deep models has attracted increasing attention for facial expression analysis as it helps to improve the performance of expression recognition accuracy despite having small number of real…

High-density object counting in surveillance scenes is challenging mainly due to the drastic variation of object scales. The prevalence of deep learning has largely boosted the object counting accuracy on several benchmark datasets.…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

Camouflaged objects that blend into natural scenes pose significant challenges for deep-learning models to detect and synthesize. While camouflaged object detection is a crucial task in computer vision with diverse real-world applications,…

Human action recognition is a challenging problem, particularly when there is high variability in factors such as subject appearance, backgrounds and viewpoint. While deep neural networks (DNNs) have been shown to perform well on action…

Estimating the number of buildings in any geographical region is a vital component of urban analysis, disaster management, and public policy decision. Deep learning methods for building localization and counting in satellite imagery, can…