Related papers: Visual recognition in the wild by sampling deep si…
Object pose estimation is important for object manipulation and scene understanding. In order to improve the general applicability of pose estimators, recent research focuses on providing estimates for novel objects, that is objects unseen…
Nowadays, deep learning methods, especially the convolutional neural networks (CNNs), have shown impressive performance on extracting abstract and high-level features from the hyperspectral image. However, general training process of CNNs…
Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation…
Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that…
Convolutional Neural Networks have become state of the art methods for image classification over the last couple of years. By now they perform better than human subjects on many of the image classification datasets. Most of these datasets…
While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training…
Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step…
Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to…
Convolutional Neural Networks (CNNs) can provide accurate object classification. They can be extended to perform object detection by iterating over dense or selected proposed object regions. However, the runtime of such detectors scales as…
The use of simulated virtual environments to train deep convolutional neural networks (CNN) is a currently active practice to reduce the (real)data-hungriness of the deep CNN models, especially in application domains in which large scale…
Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make the problem particularly difficult. In this paper, we…
Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…
Automated visual firearms classification from RGB images is an important real-world task with applications in public space security, intelligence gathering and law enforcement investigations. When applied to images massively crawled from…
There is a growing demand for accurate high-resolution land cover maps in many fields, e.g., in land-use planning and biodiversity conservation. Developing such maps has been performed using Object-Based Image Analysis (OBIA) methods, which…
Occlusions of objects is one of the indispensable problems in Computer vision. While Convolutional Neural Net-works (CNNs) provide various state of the art approaches for regular image classification, they however, prove to be not as…
The need for large annotated image datasets for training Convolutional Neural Networks (CNNs) has been a significant impediment for their adoption in computer vision applications. We show that with transfer learning an effective object…
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful…
Visual translation tolerance refers to our capacity to recognize objects over a wide range of different retinal locations. Although translation is perhaps the simplest spatial transform that the visual system needs to cope with, the extent…
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the…
Humans are generally good at learning abstract concepts about objects and scenes (e.g.\ spatial orientation, relative sizes, etc.). Over the last years convolutional neural networks have achieved almost human performance in recognizing…