Related papers: Domain Adaptation through Synthesis for Unsupervis…

While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic…

To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire because labeled medical images are not usually available due to privacy issues,…

Although the performance of person re-identification (Re-ID) has been much improved by using sophisticated training methods and large-scale labelled datasets, many existing methods make the impractical assumption that information of a…

Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these…

Cross-spectral biometrics, such as matching imagery of faces or persons from visible (RGB) and infrared (IR) bands, have rapidly advanced over the last decade due to increasing sensitivity, size, quality, and ubiquity of IR focal plane…

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…

Object detection in thermal images is an important computer vision task and has many applications such as unmanned vehicles, robotics, surveillance and night vision. Deep learning based detectors have achieved major progress, which usually…

As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution…

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the…

Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning…

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained…

Object detection algorithms allow to enable many interesting applications which can be implemented in different devices, such as smartphones and wearable devices. In the context of a cultural site, implementing these algorithms in a…

This paper proposes a method for video smoke detection using synthetic smoke samples. The virtual data can automatically offer precise and rich annotated samples. However, the learning of smoke representations will be hurt by the appearance…

Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely…

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…

In a conventional domain adaptation person Re-identification (Re-ID) task, both the training and test images in target domain are collected under the sunny weather. However, in reality, the pedestrians to be retrieved may be obtained under…

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem…

Object detection is one of the key target tasks of interest in the context of civil and military applications. In particular, the real-world deployment of target detection methods is pivotal in the decision-making process during military…

Person re-identification (re-ID) requires densely distributed cameras. In practice, the person of interest may not be captured by cameras and, therefore, needs to be retrieved using subjective information (e.g., sketches from witnesses).…

Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…