Abstract: This paper focuses on near infrared (NIR) image colorization by using a Generative Adversarial Network (GAN) architecture model. The proposed architecture consists of two stages. Firstly, it learns to colorize the given input, resulting in a RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. The proposed model starts the learning process from scratch, because our set of images is very dierent from the dataset used in existing pre-trained models, so transfer learning strategies cannot be used. Infrared image colorization is an important problem when human perception need to be considered, e.g, in remote sensing applications. Experimental results with a large set of real images are provided showing the validity of the proposed approach.

Abstract: We propose a method that aims to lessen the significant accuracy degradation
that a discriminative classifier can suffer when it is trained in a specific domain (source domain) and applied in a different one (target domain). The principal reason for this degradation is the discrepancies in the distribution of the features that feed the classifier in different domains. Therefore, we propose a domain adaptation method that maps the features from the different domains into a common subspace and learns a discriminative domain-invariant classifier within it. Our algorithm combines bilinear classifiers and multi-task learning for domain adaptation.
The bilinear classifier encodes the feature transformation and classification
parameters by a matrix decomposition. In this way, specific feature transformations for multiple domains and a shared classifier are jointly learned in a multi-task learning framework. Focusing on domain adaptation for visual object detection, we apply this method to the state-of-the-art deformable part-based model for cross domain pedestrian detection. Experimental results show that our method significantly avoids the domain drift and improves the accuracy when compared to several baselines.

Abstract: Vision-based object detectors are crucial for different applications. They rely on learnt object models. Ideally, we would like to deploy our vision system in the scenario where it must operate, and lead it to self-learn how to distinguish the objects of interest, i.e., without human intervention. However, the learning of each object model requires labelled samples collected through a tiresome manual process. For instance, we are interested in exploring the self-training of a pedestrian detector for driver assistance systems. Our first approach to avoid manual labelling consisted in the use of samples coming from realistic computer graphics, so that their labels are automatically available [12]. This would make possible the desired self-training of our pedestrian detector. However, as we showed in [14], between virtual and real worlds it may be a dataset shift. In order to overcome it, we propose the use of unsupervised domain adaptation techniques that avoid human intervention during the adaptation process. In particular, this paper explores the use of the transductive SVM (T-SVM) learning algorithm in order to adapt virtual and real worlds for pedestrian detection (Fig. 1).

Abstract: Image based human detection is of paramount interest due to its potential applications in fields such as advanced driving assistance, surveillance and media analysis. However, even detecting non-occluded standing humans remains a challenge of intensive research. The most promising human detectors rely on classifiers developed in the discriminative paradigm, i.e., trained with labelled samples. However, labeling is a manual intensive step, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, some authors have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of rendered images, i.e., using realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera, or similar ones. Accordingly, in this paper we address the challenge of using a virtual world for gathering (while playing a videogame) a large amount of automatically labelled samples (virtual humans and background) and then training a classifier that performs equal, in real-world images, than the one obtained by equally training from manually labelled real-world samples. For doing that, we cast the problem as one of domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we propose a non-standard active learning technique. Therefore, ultimately our human model is learnt by the combination of virtual and real world labelled samples (Fig. 1), which has not been done before. We present quantitative results showing that this approach is valid.