| CARVIEW |
Conferences
Metric Learning for Novelty and Anomaly Detection
Authors: Marc Masana, Idoia Ruiz, Joan Serrat, Joost Van de Weijer, Antonio M. Lopez
British Machine Vision Conference (BMVC), 2018
Abstract: When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works.
LIUM-CVC Submissions for WMT18 Multimodal Translation Task
Authors: Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, Marc Masana, Luis Herranz, Joost van de Weijer.
Publication accepted at WMT 2018 after winning the Multimodal Machine Translation challenge (WMT), 2018
Abstract: This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previous multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions ranked first for English-French and second for English-German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
Authors: Xialei Liu*, Marc Masana*, Luis Herranz, Joost Van de Weijer, Antonio M. Lopez, Andrew D Bagdanov
International Conference on Pattern Recognition (ICPR), 2018
Abstract: In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and Stanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to the state-of-the-art in lifelong learning without forgetting.
Domain-adaptive deep network compression
Authors: Marc Masana, Joost van de Weijer, Luis Herranz, Andrew D Bagdanov, Jose M Alvarez
International Conference on Computer Vision (ICCV), 2017
Abstract: Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer. We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing. We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone – with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
Lium-cvc submissions for wmt17 multimodal translation task
Authors: Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz and Joost van de Weijer.
Publication accepted at WMT 2017 after winning the Multimodal Machine Translation challenge (WMT), 2017
Abstract: This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En→De and En→Fr language pairs according to the automatic evaluation metrics METEOR and BLEU.
Hierarchical part detection with deep neural networks
Authors: Esteve Cervantes, Long Long Yu, Andrew D Bagdanov, Marc Masana, Joost van de Weijer
IEEE International Conference on Image Processing (ICIP), 2016
Abstract: Part detection is an important aspect of object recognition. Most approaches apply object proposals to generate hundreds of possible part bounding box candidates which are then evaluated by part classifiers. Recently several methods have investigated directly regressing to a limited set of bounding boxes from deep neural network representation. However, for object parts such methods may be unfeasible due to their relatively small size with respect to the image. We propose a hierarchical method for object and part detection. In a single network we first detect the object and then regress to part location proposals based only on the feature representation inside the object. Experiments show that our hierarchical approach outperforms a network which directly regresses the part locations. We also show that our approach obtains part detection accuracy comparable or better than state-of-the-art on the CUB-200 bird and Fashionista clothing item datasets with only a fraction of the number of part proposals.
Does multimodality help human and machine for translation and image captioning?
Authors: Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Joost Van de Weijer.
Publication accepted at WMT 2016 after winning the Multimodal Machine Translation challenge (WMT), 2016
Abstract: This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate the usefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.
Journals
Class-incremental learning: survey and performance evaluation on image classification
Authors: Marc Masana, Xialei Liu, Bartłomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer.
Submitted preprint, 2020
Abstract: For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored – also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task incremental learning, where a task-ID is provided at inference time. Recently we have seen a shift towards class-incremental learning where the learner must classify at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing methods for incremental learning, and in particular we perform an extensive experimental evaluation on twelve class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale datasets, investigation into small and large domain shifts, and comparison on various network architectures.
A continual learning survey: Defying forgetting in classification tasks
Authors: Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Gregory Slabaugh, Tinne Tuytelaars.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
Abstract: Artificial neural networks thrive in solving the classification problem for a particular rigid task, where the network resembles a static entity of knowledge, acquired through generalized learning behaviour from a distinct training phase. However, endeavours to extend this knowledge without targeting the original task usually result in a catastrophic forgetting of this task. Continual learning shifts this paradigm towards a network that can continually accumulate knowledge over different tasks without the need for retraining from scratch, with methods in particular aiming to alleviate forgetting. We focus on task-incremental classification, where tasks arrive in a batch-like fashion, and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 10 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize which method performs best, both on balanced Tiny Imagenet and a large-scale unbalanced iNaturalist datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.
Automated mitral valve vortex ring extraction from 4D‐flow MRI
Authors: Corina Kräuter, Ursula Reiter, Clemens Reiter, Volha Nizhnikava, Marc Masana, Albrecht Schmidt, Michael Fuchsjäger, Rudolf Stollberger, Gert Reiter.
Magnetic Resonance in Medicine (MRM), 2020
Abstract: Purpose: To present and validate a method for automated extraction and analysis of the temporal evolution of the mitral valve (MV) vortex ring from MR 4D‐flow data. Methods: The proposed algorithm uses the divergence‐free part of the velocity vector field for Q criterion‐based identification and tracking of MV vortex ring core and region within the left ventricle (LV). The 4D‐flow data of 20 subjects (10 healthy controls, 10 patients with ischemic heart disease) were used to validate the algorithm against visual analysis as well as to assess the method’s sensitivity to manual LV segmentation. Quantitative MV vortex ring parameters were analyzed with respect to both their differences between healthy subjects and patients and their correlation with transmitral peak velocities. Results: The algorithm successfully extracted MV vortex rings throughout the entire cardiac cycle, which agreed substantially with visual analysis (Cohen’s kappa =0.77). Furthermore, vortex cores and regions were robustly detected even if a static end-diastolic LV segmentation mask was applied to all frames (Dice coefficients 0.82 ± 0.08 and 0.94 ± 0.02 for core and region, respectively). Early diastolic MV vortex ring vorticity, kinetic energy and circularity index differed significantly between healthy controls and patients. In contrast to vortex shape parameters, vorticity and kinetic energy correlated strongly with transmitral peak velocities. Conclusion: An automated method for temporal MV vortex ring extraction demonstrating robustness with respect to LV segmentation strategies is introduced. Quantitative vortex parameter analysis indicates importance of the MV vortex ring for LV diastolic (dys)function.
Saliency from High-Level Semantic Image Features
Authors: Aymen Azaza, Joost van de Weijer, Ali Douik, Javad Zolfaghari, Marc Masana.
SN Computer Science (Springer), 2020
Abstract: Top-down semantic information is known to play an important role in assigning saliency. Recently, large strides have been made in improving state-of-the-art semantic image understanding in the fields of object detection and semantic segmentation. Therefore, since these methods have now reached a high-level of maturity, evaluation of the impact of high-level image understanding on saliency estimation is now feasible. We propose several saliency features which are computed from object detection and semantic segmentation results. We combine these features with a standard baseline method for saliency detection to evaluate their importance. Experiments demonstrate that the proposed features derived from object detection and semantic segmentation improve saliency estimation significantly. Moreover, they show that our method obtains state-of-the-art results on (FT, ImgSal, and SOD datasets) and obtains competitive results on four other datasets (ECSSD, PASCAL-S, MSRA-B, and HKU-IS).
GTCreator: a Flexible Annotation Tool for Image-based Datasets
Authors: Jorge Bernal, Aymeric Histace, Marc Masana, Quentin Angermann, Cristina Sánchez-Montes, Cristina Rodríguez de Miguel, Maroua Hammami, Ana García-Rodríguez, Henry Córdova, Olivier Romain, Gloria Fernández-Esparrach, Xavier Dray, F. Javier Sánchez.
International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2018
Abstract: Purpose: Method evaluation for decision support systems for health is a time consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use. Methods: We introduce GTCreator, a flexible annotation tool for providing image and text annotations to image-based datasets. It keeps the main functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing. Results: The comparison with other similar tools show that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites. As a use case of our tool, we present three different benchmarks generated using our tool covering all stages in polyp characterization: detection, segementation and histology prediction. Conclusions: Our proposed annotation tool has been proven to be efficient for large image dataset annotation, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis.
Context Proposals for Saliency Detection
Authors: Aymen Azaza, Joost van de Weijer, Ali Douik, Marc Masana.
Journal on Computer Vision and Image Understanding (CVIU), 2018
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).
Workshops
On the importance of cross-task features for class-incremental learning
Authors: Albin Soutif--Cormerais, Marc Masana, Joost Van de Weijer, Bartłomiej Twardowski.
International Conference on Machine Learning - Theory and Foundation in Continual Learning (ICML-W), 2021
Abstract: In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform cross-task discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of cross-task features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features. This is especially important when the number of classes per task is small.
Ternary Feature Masks: zero-forgetting for task-incremental learning
Authors: Marc Masana, Tinne Tuytelaars, Joost van de Weijer.
Computer Vision and Pattern Recognition - Workshop on Continual Learning (CLVISION), 2021
Abstract: We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue--and show experimentally--that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches.
Avalanche: an End-to-End Library for Continual Learning
Authors: Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido M van de Ven, Martin Mundt, Qi She, Keiland Cooper, Jeremy Forest, Eden Belouadah, Simone Calderara, German I Parisi, Fabio Cuzzolin, Andreas S Tolias, Simone Scardapane, Luca Antiga, Subutai Ahmad, Adrian Popescu, Christopher Kanan, Joost van de Weijer, Tinne Tuytelaars, Davide Bacciu, Davide Maltoni.
Computer Vision and Pattern Recognition - Workshop on Continual Learning (CLVISION), 2021
Abstract: Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
On Class Orderings for Incremental Learning
Authors: Marc Masana, Bartłomiej Twardowski, Joost van de Weijer
International Conference on Machine Learning - Workshop on Continual Learning (CL-ICML), 2020
Abstract: The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods.
Disentanglement of Color and Shape Representations for Continual Learning
Authors: David Berga, Marc Masana, Joost Van de Weijer
International Conference on Machine Learning - Workshop on Continual Learning (CL-ICML), 2020
Abstract: We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification accuracy and forgetting in a task-incremental setting with Oxford-102 Flowers dataset. We combine our method with Elastic Weight Consolidation, Learning without Forgetting, Synaptic Intelligence and Memory Aware Synapses, and show that feature disentanglement positively impacts continual learning performance.
On-the-fly Network Pruning for Object Detection
Authors: Marc Masana, Joost van de Weijer, Andrew D Bagdanov
International Conference on Learning Representations (ICLR), 2016
Abstract: Object detection with deep neural networks is often performed by passing a few thousand candidate bounding boxes through a deep neural network for each image. These bounding boxes are highly correlated since they originate from the same image. In this paper we investigate how to exploit feature occurrence at the image scale to prune the neural network which is subsequently applied to all bounding boxes. We show that removing units which have near-zero activation in the image allows us to significantly reduce the number of parameters in the network. Results on the PASCAL 2007 Object Detection Challenge demonstrate that up to 40% of units in some fully-connected layers can be entirely eliminated with little change in the detection result.
Books
Lifelong Learning of Neural Networks: Detecting Novelty and Adapting to New Domains without Forgetting
Authors: Marc Masana
PhD thesis, 2020
Abstract: Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time. We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information based on activation statistics. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost. Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques (both when knowing the task-ID at test time or not) and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of mask parameters to be added for each new task; with more than three orders of magnitude for most networks. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias. We also consider the problem of out-of-distribution detection. Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.
Interactive Visual and Semantic Image Retrieval
Authors: Joost Van De Weijer, Fahad Khan, Marc Masana
Multimodal Interaction in Image and Video Applications (pages 31-45), Springer 2013
Intro: One direct consequence of recent advances in digital visual data generation and the direct availability of this information through the World-Wide Web, is a urgent demand for efficient image retrieval systems. The objective of image retrieval is to allow users to efficiently browse through this abundance of images. Due to the non-expert nature of the majority of the internet users, such systems should be user friendly, and therefore avoid complex user interfaces. In this chapter we investigate how high-level information provided by recently developed object recognition techniques can improve interactive image retrieval. We apply a bag-of-word based image representation method to automatically classify images in a number of categories. These additional labels are then applied to improve the image retrieval system. Next to these high-level semantic labels, we also apply a low-level [...]
Projects
Spanish Ministry funding
Deep Multi-Task Learning for Object Recognition
MINECO “Excelencia” funding
Closing the loop: bio-inspired top-down feedback for computational vision systems
Master Thesis:
Context-based pruning for scalable object detection
Advisors: Andrew D. Bagdanov and Joost van de Weijer
Abstract: Most existing approaches to object detection scale linearly with the number of classes. We investigate several pruning strategies which result in sub-linear scaling. We exploit fast context classification based on deep features to select a reduced set of detectors. This prevents the unnecessary computation of detectors which are not expected within the context. Results show a linear speed-up in the number of classes on action recognition and a 5 times speed-up for general object detection with a negligible loss of accuracy. In addition, we show how the proposed pruning strategies can be incorporated into the fully connected layers of Deep Convolutional Neural Networks.
Work Experience
Post-doc - Computer Vision Center (Des 2020 - Apr 2021)
Collaborate within the Learning and Machine Perception (LAMP) group mainly on continual learning projects.
PhD Stay - KU Leuven - PSI group (May 2018 - Aug 2018)
Research on LifeLong Learning under the supervision of Tinne Tuytelaars.
Knowledge Transfer - International Automotive Company (Jun 2017 - Mar 2018)
Research and implementation of a framework including novelty/anomaly detection, data generation and lifelong learning methods.
Knowledge Transfer - EURECAT (Apr 2016 - Sep 2016)
Assist on the master thesis of Olaia Artieda “Automatic MEME discovery” about distance learning with siamese and triplet networks.
Knowledge Transfer - SADAKO Technologies (Dec 2014 - Aug 2015)
Assist in the design and optimization of a Computer Vision pipeline.
Support researcher - Computer Vision Center (Mar 2012 - Jul 2015)
Collaborate within the Color in Context (CiC) and the Learning and Machine Perception (LAMP) groups at different research projects on the topics of: image classification, object recognition and detection, image retrieval, illuminant estimation, color descriptors and neural network pruning.
Scholarship holder - Institute of Law and Technology (Feb 2009 - Feb 2012)
Collaborate at different research projects with database management, webpage management and video transcription.
Seminars and Lectures
Seminar - KU Leuven - PSI Seminar (May 2018)
"Two talks on Deep Networks”, by Marc Masana. Presentation on "Domain-adaptive deep network compression" and "Rotate your Networks".
Lecture - BigSkyEarth Training School (Apr 2018)
"Deep Learning Frameworks”, by Marc Masana. COST Action. Special focus on Tensorflow, Tensorboard and PyTorch. Hands-on session on Tensorflow (code).
Lecture - Master in Computer Vision (Mar 2018)
"Deep Learning Frameworks”, by Marc Masana. Special focus on Tensorflow, Tensorboard and PyTorch. Master in Computer Vision Module 5.
Seminar - LifeLong Learning Seminar (Feb 2018)
"Lifelong Learning Seminar”, by Joan Serrà, Xialei Liu and Marc Masana. CVC Seminars.
Lecture - Master in Computer Vision (Mar 2017)
"Deep Learning Frameworks”, by Joan Serrat and Marc Masana. Special focus on Caffe and Matconvnet. Master in Computer Vision Module 5.
Seminar - Hands-On Deep Learning (Mar 2016)
This is an attempt of showing practical concepts of deep learning and convolutional neural networks (CNNs) through useful examples using the MatConvNet framework. 6 week seminar with theoretical and hands-on sessions by German Ros, Joost van de Weijer, Marc Masana and Yaxing Wang.
Bio
I received my B.Sc. degrees in Mathematics and Computer Science from the Universitat Autònoma de Barcelona in 2014 and my M.Sc. degree (with honours) in Computer Vision from the Universitat Autònoma de Barcelona (UAB) in 2015. I finished at Top 5 and was awarded as "Best Master Thesis". In 2012 I joined the Computer Vision Center as Support Researcher. I obtained a Ph.D. degree under the supervision of Dr. Joost van de Weijer and Dr. Andrew D. Bagdanov in 2020. My main research interests include Deep Neural Networks, Object Detection, Network Compression and Continual Learning.