Pau Rodriguez, Miguel Angel Bautista, Sergio Escalera, & Jordi Gonzalez. (2018). Beyond Oneshot Encoding: lower dimensional target embedding. IMAVIS - Image and Vision Computing, 75, 21–31.
Abstract: Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates.
Keywords: Error correcting output codes; Output embeddings; Deep learning; Computer vision
|
Aymen Azaza, Joost Van de Weijer, Ali Douik, & Marc Masana. (2018). Context Proposals for Saliency Detection. CVIU - Computer Vision and Image Understanding, 174, 1–11.
Abstract: One of the fundamental properties of a salient object region is its contrast
with the immediate context. The problem is that numerous object regions
exist which potentially can all be salient. One way to prevent an exhaustive
search over all object regions is by using object proposal algorithms. These
return a limited set of regions which are most likely to contain an object. Several saliency estimation methods have used object proposals. However, they focus on the saliency of the proposal only, and the importance of its immediate context has not been evaluated.
In this paper, we aim to improve salient object detection. Therefore, we extend object proposal methods with context proposals, which allow to incorporate the immediate context in the saliency computation. We propose several saliency features which are computed from the context proposals. In the experiments, we evaluate five object proposal methods for the task of saliency segmentation, and find that Multiscale Combinatorial Grouping outperforms the others. Furthermore, experiments show that the proposed context features improve performance, and that our method matches results on the FT datasets and obtains competitive results on three other datasets (PASCAL-S, MSRA-B and ECSSD).
|
Maedeh Aghaei, Mariella Dimiccoli, C. Canton-Ferrer, & Petia Radeva. (2018). Towards social pattern characterization from egocentric photo-streams. CVIU - Computer Vision and Image Understanding, 171, 104–117.
Abstract: Following the increasingly popular trend of social interaction analysis in egocentric vision, this article presents a comprehensive pipeline for automatic social pattern characterization of a wearable photo-camera user. The proposed framework relies merely on the visual analysis of egocentric photo-streams and consists of three major steps. The first step is to detect social interactions of the user where the impact of several social signals on the task is explored. The detected social events are inspected in the second step for categorization into different social meetings. These two steps act at event-level where each potential social event is modeled as a multi-dimensional time-series, whose dimensions correspond to a set of relevant features for each task; finally, LSTM is employed to classify the time-series. The last step of the framework is to characterize social patterns of the user. Our goal is to quantify the duration, the diversity and the frequency of the user social relations in various social situations. This goal is achieved by the discovery of recurrences of the same people across the whole set of social events related to the user. Experimental evaluation over EgoSocialStyle – the proposed dataset in this work, and EGO-GROUP demonstrates promising results on the task of social pattern characterization from egocentric photo-streams.
Keywords: Social pattern characterization; Social signal extraction; Lifelogging; Convolutional and recurrent neural networks
|
Sumit K. Banchhor, Narendra D. Londhe, Tadashi Araki, Luca Saba, Petia Radeva, Narendra N. Khanna, et al. (2018). Calcium detection, its quantification, and grayscale morphology-based risk stratification using machine learning in multimodality big data coronary and carotid scans: A review. CBM - Computers in Biology and Medicine, 101, 184–198.
Abstract: Purpose of review
Atherosclerosis is the leading cause of cardiovascular disease (CVD) and stroke. Typically, atherosclerotic calcium is found during the mature stage of the atherosclerosis disease. It is therefore often a challenge to identify and quantify the calcium. This is due to the presence of multiple components of plaque buildup in the arterial walls. The American College of Cardiology/American Heart Association guidelines point to the importance of calcium in the coronary and carotid arteries and further recommend its quantification for the prevention of heart disease. It is therefore essential to stratify the CVD risk of the patient into low- and high-risk bins.
Recent finding
Calcium formation in the artery walls is multifocal in nature with sizes at the micrometer level. Thus, its detection requires high-resolution imaging. Clinical experience has shown that even though optical coherence tomography offers better resolution, intravascular ultrasound still remains an important imaging modality for coronary wall imaging. For a computer-based analysis system to be complete, it must be scientifically and clinically validated. This study presents a state-of-the-art review (condensation of 152 publications after examining 200 articles) covering the methods for calcium detection and its quantification for coronary and carotid arteries, the pros and cons of these methods, and the risk stratification strategies. The review also presents different kinds of statistical models and gold standard solutions for the evaluation of software systems useful for calcium detection and quantification. Finally, the review concludes with a possible vision for designing the next-generation system for better clinical outcomes.
Keywords: Heart disease; Stroke; Atherosclerosis; Intravascular; Coronary; Carotid; Calcium; Morphology; Risk stratification
|
Oscar Argudo, Marc Comino, Antonio Chica, Carlos Andujar, & Felipe Lumbreras. (2018). Segmentation of aerial images for plausible detail synthesis. CG - Computers & Graphics, 71, 23–34.
Abstract: The visual enrichment of digital terrain models with plausible synthetic detail requires the segmentation of aerial images into a suitable collection of categories. In this paper we present a complete pipeline for segmenting high-resolution aerial images into a user-defined set of categories distinguishing e.g. terrain, sand, snow, water, and different types of vegetation. This segmentation-for-synthesis problem implies that per-pixel categories must be established according to the algorithms chosen for rendering the synthetic detail. This precludes the definition of a universal set of labels and hinders the construction of large training sets. Since artists might choose to add new categories on the fly, the whole pipeline must be robust against unbalanced datasets, and fast on both training and inference. Under these constraints, we analyze the contribution of common per-pixel descriptors, and compare the performance of state-of-the-art supervised learning algorithms. We report the findings of two user studies. The first one was conducted to analyze human accuracy when manually labeling aerial images. The second user study compares detailed terrains built using different segmentation strategies, including official land cover maps. These studies demonstrate that our approach can be used to turn digital elevation models into fully-featured, detailed terrains with minimal authoring efforts.
Keywords: Terrain editing; Detail synthesis; Vegetation synthesis; Terrain rendering; Image segmentation
|
Antonio Lopez, David Vazquez, & Gabriel Villalonga. (2018). Data for Training Models, Domain Adaptation. In Intelligent Vehicles. Enabling Technologies and Future Developments (395–436).
Abstract: Simulation can enable several developments in the field of intelligent vehicles. This chapter is divided into three main subsections. The first one deals with driving simulators. The continuous improvement of hardware performance is a well-known fact that is allowing the development of more complex driving simulators. The immersion in the simulation scene is increased by high fidelity feedback to the driver. In the second subsection, traffic simulation is explained as well as how it can be used for intelligent transport systems. Finally, it is rather clear that sensor-based perception and action must be based on data-driven algorithms. Simulation could provide data to train and test algorithms that are afterwards implemented in vehicles. These tools are explained in the third subsection.
Keywords: Driving simulator; hardware; software; interface; traffic simulation; macroscopic simulation; microscopic simulation; virtual data; training data
|
Jose M. Armingol, Jorge Alfonso, Nourdine Aliane, Miguel Clavijo, Sergio Campos-Cordobes, Arturo de la Escalera, et al. (2018). Environmental Perception for Intelligent Vehicles. In Intelligent Vehicles. Enabling Technologies and Future Developments (23–101).
Abstract: Environmental perception represents, because of its complexity, a challenge for Intelligent Transport Systems due to the great variety of situations and different elements that can happen in road environments and that must be faced by these systems. In connection with this, so far there are a variety of solutions as regards sensors and methods, so the results of precision, complexity, cost, or computational load obtained by these works are different. In this chapter some systems based on computer vision and laser techniques are presented. Fusion methods are also introduced in order to provide advanced and reliable perception systems.
Keywords: Computer vision; laser techniques; data fusion; advanced driver assistance systems; traffic monitoring systems; intelligent vehicles
|
Patricia Suarez, Angel Sappa, & Boris X. Vintimilla. (2018). Vegetation Index Estimation from Monospectral Images. In 15th International Conference on Images Analysis and Recognition (Vol. 10882, pp. 353–362). LNCS.
Abstract: This paper proposes a novel approach to estimate Normalized Difference Vegetation Index (NDVI) from just the red channel of a RGB image. The NDVI index is defined as the ratio of the difference of the red and infrared radiances over their sum. In other words, information from the red channel of a RGB image and the corresponding infrared spectral band are required for its computation. In the current work the NDVI index is estimated just from the red channel by training a Conditional Generative Adversarial Network (CGAN). The architecture proposed for the generative network consists of a single level structure, which combines at the final layer results from convolutional operations together with the given red channel with Gaussian noise to enhance
details, resulting in a sharp NDVI image. Then, the discriminative model
estimates the probability that the NDVI generated index came from the training dataset, rather than the index automatically generated. Experimental results with a large set of real images are provided showing that a Conditional GAN single level model represents an acceptable approach to estimate NDVI index.
|
Vacit Oguz Yazici, Joost Van de Weijer, & Arnau Ramisa. (2018). Color Naming for Multi-Color Fashion Items. In 6th World Conference on Information Systems and Technologies (Vol. 747, pp. 64–73).
Abstract: There exists a significant amount of research on color naming of single colored objects. However in reality many fashion objects consist of multiple colors. Currently, searching in fashion datasets for multi-colored objects can be a laborious task. Therefore, in this paper we focus on color naming for images with multi-color fashion items. We collect a dataset, which consists of images which may have from one up to four colors. We annotate the images with the 11 basic colors of the English language. We experiment with several designs for deep neural networks with different losses. We show that explicitly estimating the number of colors in the fashion item leads to improved results.
Keywords: Deep learning; Color; Multi-label
|
Lei Kang, Juan Ignacio Toledo, Pau Riba, Mauricio Villegas, Alicia Fornes, & Marçal Rusiñol. (2018). Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition. In 40th German Conference on Pattern Recognition (pp. 459–472).
Abstract: This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.
|
Mohamed Ilyes Lakhal, Albert Clapes, Sergio Escalera, Oswald Lanz, & Andrea Cavallaro. (2018). Residual Stacked RNNs for Action Recognition. In 9th International Workshop on Human Behavior Understanding (pp. 534–548).
Abstract: Action recognition pipelines that use Recurrent Neural Networks (RNN) are currently 5–10% less accurate than Convolutional Neural Networks (CNN). While most works that use RNNs employ a 2D CNN on each frame to extract descriptors for action recognition, we extract spatiotemporal features from a 3D CNN and then learn the temporal relationship of these descriptors through a stacked residual recurrent neural network (Res-RNN). We introduce for the first time residual learning to counter the degradation problem in multi-layer RNNs, which have been successful for temporal aggregation in two-stream action recognition pipelines. Finally, we use a late fusion strategy to combine RGB and optical flow data of the two-stream Res-RNN. Experimental results show that the proposed pipeline achieves competitive results on UCF-101 and state of-the-art results for RNN-like architectures on the challenging HMDB-51 dataset.
Keywords: Action recognition; Deep residual learning; Two-stream RNN
|
Felipe Codevilla, Antonio Lopez, Vladlen Koltun, & Alexey Dosovitskiy. (2018). On Offline Evaluation of Vision-based Driving Models. In 15th European Conference on Computer Vision (Vol. 11219, pp. 246–262). LNCS.
Abstract: Autonomous driving models should ideally be evaluated by deploying
them on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vast majority of researchers. An attractive alternative is to evaluate models offline, on a pre-collected validation dataset with ground truth annotation. In this paper, we investigate the relation between various online and offline metrics for evaluation of autonomous driving models. We find that offline prediction error is not necessarily correlated with driving quality, and two models with identical prediction error can differ dramatically in their driving performance. We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset and
suitable offline metrics.
Keywords: Autonomous driving; deep learning
|
Marc Oliu, Javier Selva, & Sergio Escalera. (2018). Folded Recurrent Neural Networks for Future Video Prediction. In 15th European Conference on Computer Vision (Vol. 11218, pp. 745–761). LNCS.
Abstract: Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach.
|
Lluis Gomez, Andres Mafla, Marçal Rusiñol, & Dimosthenis Karatzas. (2018). Single Shot Scene Text Retrieval. In 15th European Conference on Computer Vision (Vol. 11218, pp. 728–744). LNCS.
Abstract: Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image
database. Our experiments demonstrate that the proposed architecture
outperforms previous state-of-the-art while it offers a significant increase
in processing speed.
Keywords: Image retrieval; Scene text; Word spotting; Convolutional Neural Networks; Region Proposals Networks; PHOC
|
Ciprian Corneanu, Meysam Madadi, & Sergio Escalera. (2018). Deep Structure Inference Network for Facial Action Unit Recognition. In 15th European Conference on Computer Vision (Vol. 11216, pp. 309–324). LNCS.
Abstract: Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Recently, efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between AUs. We propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
Keywords: Computer Vision; Machine Learning; Deep Learning; Facial Expression Analysis; Facial Action Units; Structure Inference
|
