Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Tabernik, Domen"'
Object counting and localization problems are commonly addressed with point supervised learning, which allows the use of less labor-intensive point annotations. However, learning based on point annotations poses challenges due to the high imbalance b
Externí odkaz:
http://arxiv.org/abs/2408.14457
Object grasping is a fundamental challenge in robotics and computer vision, critical for advancing robotic manipulation capabilities. Deformable objects, like fabrics and cloths, pose additional challenges due to their non-rigid nature. In this work,
Externí odkaz:
http://arxiv.org/abs/2408.14456
Deep-learning methods have recently started being employed for addressing surface-defect detection problems in industrial quality control. However, with a large amount of data needed for learning, often requiring high-precision labels, many industria
Externí odkaz:
http://arxiv.org/abs/2104.06064
Segmentation-based, two-stage neural network has shown excellent results in the surface defect detection, enabling the network to learn from a relatively small number of samples. In this work, we introduce end-to-end training of the two-stage network
Externí odkaz:
http://arxiv.org/abs/2007.07676
Publikováno v:
In Construction and Building Materials 8 December 2023 408
Autor:
Tabernik, Domen, Skočaj, Danijel
Automatic detection and recognition of traffic signs plays a crucial role in management of the traffic-sign inventory. It provides accurate and timely way to manage traffic-sign inventory with a minimal human effort. In the computer vision community
Externí odkaz:
http://arxiv.org/abs/1904.00649
Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the most suitabl
Externí odkaz:
http://arxiv.org/abs/1903.08536
Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions involve l
Externí odkaz:
http://arxiv.org/abs/1902.07474
Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters. In this paper we propose a novel displaced
Externí odkaz:
http://arxiv.org/abs/1711.11473
Hierarchical feature learning based on convolutional neural networks (CNN) has recently shown significant potential in various computer vision tasks. While allowing high-quality discriminative feature learning, the downside of CNNs is the lack of exp
Externí odkaz:
http://arxiv.org/abs/1609.03795