Abstract: Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain object classes within an image, the learning of the involved classifiers turns out to be a practical bottleneck. The reason is that, at least, we have to frame object examples with bounding boxes in thousands of images. A priori, the more complex the model is regarding its number of parameters, the more annotated examples are required. This annotation task is performed by human oracles, which ends up in inaccuracies and errors in the annotations (aka ground truth) since the task is inherently very cumbersome and sometimes ambiguous. As an alternative we have pioneered the use of virtual worlds for collecting such annotations automatically and with high precision. However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA). In this chapter we revisit the DA of a deformable part-based model (DPM) as an exemplifying case of virtual- to-real-world DA. As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data. While doing so, we investigate questions such as: how does the domain gap behave due to virtual-vs-real data with respect to dominant object appearance per domain, as well as the role of photo-realism in the virtual world.

Abstract: Motivated by the success of powerful while expensive techniques to recognize words in a holistic way (Goel et al., 2013; Almazán et al., 2014; Jaderberg et al., 2016) object proposals techniques emerge as an alternative to the traditional text detectors. In this paper we introduce a novel object proposals method that is specifically designed for text. We rely on a similarity based region grouping algorithm that generates a hierarchy of word hypotheses. Over the nodes of this hierarchy it is possible to apply a holistic word recognition method in an efficient way.
Our experiments demonstrate that the presented method is superior in its ability of producing good quality word proposals when compared with class-independent algorithms. We show impressive recall rates with a few thousand proposals in different standard benchmarks, including focused or incidental text datasets, and multi-language scenarios. Moreover, the combination of our object proposals with existing whole-word recognizers (Almazán et al., 2014; Jaderberg et al., 2016) shows competitive performance in end-to-end word spotting, and, in some benchmarks, outperforms previously published results. Concretely, in the challenging ICDAR2015 Incidental Text dataset, we overcome in more than 10% F-score the best-performing method in the last ICDAR Robust Reading Competition (Karatzas, 2015). Source code of the complete end-to-end system is available at https://github.com/lluisgomez/TextProposals.

Abstract: End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.

Abstract: This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.