Abstract: Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.

Abstract: Pedestrian accidents are one of the leading preventable causes of death. In order to reduce the number of accidents, in the last decade the pedestrian protection systems have been introduced, a special type of advanced driver assistance systems, in witch an on-board camera explores the road ahead for possible collisions with pedestrians in order to warn the driver or perform braking actions. As a result of the variability of the appearance, pose and size, pedestrian detection is a very challenging task. So many techniques, models and features have been proposed to solve the problem. As the appearance of pedestrians varies signicantly as a function of distance, a system based on multiple classiers specialized on diferent depths is likely to improve the overall performance with respect to a typical system based on a general detector. Accordingly, the main aim of this work is to explore the eect of the distance in pedestrian detection. We have evaluated three pedestrian detectors (HOG, HAAR and EOH) in two dierent databases (INRIA and Daimler09) for two dierent sizes (small and big). By a extensive set of experiments we answer to questions like which datasets and evaluation methods are the most adequate, which is the best method for each size of the pedestrians and why or how do the method optimum parameters vary with respect to the distance

Abstract: Natural and intuitive human interaction with robotic systems is a key point to develop robots assisting people in an easy and effective way. In this paper, a Human Robot Interaction (HRI) system able to recognize gestures usually employed in human non-verbal communication is introduced, and an in-depth study of its usability is performed. The system deals with dynamic gestures such as waving or nodding which are recognized using a Dynamic Time Warping approach based on gesture specific features computed from depth maps. A static gesture consisting in pointing at an object is also recognized. The pointed location is then estimated in order to detect candidate objects the user may refer to. When the pointed object is unclear for the robot, a disambiguation procedure by means of either a verbal or gestural dialogue is performed. This skill would lead to the robot picking an object in behalf of the user, which could present difficulties to do it by itself. The overall system — which is composed by a NAO and Wifibot robots, a KinectTM v2 sensor and two laptops — is firstly evaluated in a structured lab setup. Then, a broad set of user tests has been completed, which allows to assess correct performance in terms of recognition rates, easiness of use and response times.

Abstract: Saffron is a well-known product in the food industry. It is one of the spices that are sometimes adulterated with the sole motive of gaining more economic profit. Today, machine vision systems are widely used in controlling the quality of food and agricultural products as a new, non-destructive, and inexpensive approach. In this study, a machine vision system based on deep learning was used to detect fraud and saffron quality. A dataset of 1869 images was created and categorized in 6 classes including: dried saffron stigma using a dryer; dried saffron stigma using pressing method; pure stem of saffron; sunflower; saffron stem mixed with food coloring; and corn silk mixed with food coloring. A Learning-to-Augment incorporated Inception-v4 Convolutional Neural Network (LAII-v4 CNN) was developed for grading and fraud detection of saffron in images captured by smartphones. The best policies of data augmentation were selected with the proposed LAII-v4 CNN using images corrupted by Gaussian, speckle, and impulse noise to address overfitting the model. The proposed LAII-v4 CNN compared with regular CNN-based methods and traditional classifiers. Ensemble of Bagged Decision Trees, Ensemble of Boosted Decision Trees, k-Nearest Neighbor, Random Under-sampling Boosted Trees, and Support Vector Machine were used for classification of the features extracted by Histograms of Oriented Gradients and Local Binary Patterns, and selected by the Principal Component Analysis. The results showed that the proposed LAII-v4 CNN with an accuracy of 99.5% has achieved the best performance by employing batch normalization, Dropout, and leaky ReLU.

Abstract: Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.