Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	76–90 of 741 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >> [11–20]

List View

Citations

Details

	Records
	Author	Cesar de Souza; Adrien Gaidon; Yohann Cabon; Naila Murray; Antonio Lopez
	Title	Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models			Type	Journal Article
	Year	2020	Publication	International Journal of Computer Vision	Abbreviated Journal	IJCV
	Volume	128	Issue		Pages	1505–1536
	Keywords	Procedural generation; Human action recognition; Synthetic data; Physics
	Abstract	Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS; 600.124; 600.118			Approved	no
	Call Number	Admin @ si @ SGC2019			Serial	3303
Permanent link to this record



	Author	Jorge Bernal; F. Javier Sanchez; Gloria Fernandez Esparrach; Debora Gil; Cristina Rodriguez de Miguel; Fernando Vilariño
	Title	WM-DOVA Maps for Accurate Polyp Highlighting in Colonoscopy: Validation vs. Saliency Maps from Physicians			Type	Journal Article
	Year	2015	Publication	Computerized Medical Imaging and Graphics	Abbreviated Journal	CMIG
	Volume	43	Issue		Pages	99-111
	Keywords	Polyp localization; Energy Maps; Colonoscopy; Saliency; Valley detection
	Abstract	We introduce in this paper a novel polyp localization method for colonoscopy videos. Our method is based on a model of appearance for polyps which defines polyp boundaries in terms of valley information. We propose the integration of valley information in a robust way fostering complete, concave and continuous boundaries typically associated to polyps. This integration is done by using a window of radial sectors which accumulate valley information to create WMDOVA1 energy maps related with the likelihood of polyp presence. We perform a double validation of our maps, which include the introduction of two new databases, including the first, up to our knowledge, fully annotated database with clinical metadata associated. First we assess that the highest value corresponds with the location of the polyp in the image. Second, we show that WM-DOVA energy maps can be comparable with saliency maps obtained from physicians' fixations obtained via an eye-tracker. Finally, we prove that our method outperforms state-of-the-art computational saliency results. Our method shows good performance, particularly for small polyps which are reported to be the main sources of polyp miss-rate, which indicates the potential applicability of our method in clinical practice.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0895-6111	ISBN		Medium
	Area		Expedition		Conference
	Notes	MV; IAM; 600.047; 600.060; 600.075;SIAI			Approved	no
	Call Number	Admin @ si @ BSF2015			Serial	2609
Permanent link to this record



	Author	Julio C. S. Jacques Junior; Yagmur Gucluturk; Marc Perez; Umut Guçlu; Carlos Andujar; Xavier Baro; Hugo Jair Escalante; Isabelle Guyon; Marcel A. J. van Gerven; Rob van Lier; Sergio Escalera
	Title	First Impressions: A Survey on Vision-Based Apparent Personality Trait Analysis			Type	Journal Article
	Year	2022	Publication	IEEE Transactions on Affective Computing	Abbreviated Journal	TAC
	Volume	13	Issue	1	Pages	75-95
	Keywords	Personality computing; first impressions; person perception; big-five; subjective bias; computer vision; machine learning; nonverbal signals; facial expression; gesture; speech analysis; multi-modal recognition
	Abstract	Personality analysis has been widely studied in psychology, neuropsychology, and signal processing fields, among others. From the past few years, it also became an attractive research area in visual computing. From the computational point of view, by far speech and text have been the most considered cues of information for analyzing personality. However, recently there has been an increasing interest from the computer vision community in analyzing personality from visual data. Recent computer vision approaches are able to accurately analyze human faces, body postures and behaviors, and use these information to infer apparent personality traits. Because of the overwhelming research interest in this topic, and of the potential impact that this sort of methods could have in society, we present in this paper an up-to-date review of existing vision-based approaches for apparent personality trait recognition. We describe seminal and cutting edge works on the subject, discussing and comparing their distinctive features and limitations. Future venues of research in the field are identified and discussed. Furthermore, aspects on the subjectivity in data labeling/evaluation, as well as current datasets and challenges organized to push the research on the field are reviewed.
	Address	1 Jan.-March 2022
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	HuPBA			Approved	no
	Call Number	Admin @ si @ JGP2022			Serial	3724
Permanent link to this record



	Author	Idoia Ruiz; Bogdan Raducanu; Rakesh Mehta; Jaume Amores
	Title	Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation			Type	Journal Article
	Year	2020	Publication	Engineering Applications of Artificial Intelligence	Abbreviated Journal	EAAI
	Volume	87	Issue		Pages	103309
	Keywords	Person re-identification; Network distillation; Image retrieval; Model compression; Surveillance
	Abstract	Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between accuracy and speed. We analyse this trade-off, comparing a classical method, that comprises hand-crafted feature description and metric learning, in particular, LOMO and XQDA, to deep learning based techniques, using image classification networks, ResNet and MobileNets. Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time. We evaluate both methods on the Market-1501 and DukeMTMC-reID large-scale datasets, showing that distillation helps reducing the computational cost at inference time while even increasing the accuracy performance.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	LAMP; 600.109; 600.120			Approved	no
	Call Number	Admin @ si @ RRM2020			Serial	3401
Permanent link to this record



	Author	Marçal Rusiñol; Josep Llados
	Title	A Performance Evaluation Protocol for Symbol Spotting Systems in Terms of Recognition and Location Indices			Type	Journal Article
	Year	2009	Publication	International Journal on Document Analysis and Recognition	Abbreviated Journal	IJDAR
	Volume	12	Issue	2	Pages	83-96
	Keywords	Performance evaluation; Symbol Spotting; Graphics Recognition
	Abstract	Symbol spotting systems are intended to retrieve regions of interest from a document image database where the queried symbol is likely to be found. They shall have the ability to recognize and locate graphical symbols in a single step. In this paper, we present a set of measures to evaluate the performance of a symbol spotting system in terms of recognition abilities, location accuracy and scalability. We show that the proposed measures allow to determine the weaknesses and strengths of different methods. In particular we have tested a symbol spotting method based on a set of four different off-the-shelf shape descriptors.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1433-2833	ISBN		Medium
	Area		Expedition		Conference
	Notes	DAG			Approved	no
	Call Number	DAG @ dag @ RuL2009a			Serial	1166
Permanent link to this record



	Author	Maria Oliver; G. Haro; Mariella Dimiccoli; B. Mazin; C. Ballester
	Title	A Computational Model for Amodal Completion			Type	Journal Article
	Year	2016	Publication	Journal of Mathematical Imaging and Vision	Abbreviated Journal	JMIV
	Volume	56	Issue	3	Pages	511–534
	Keywords	Perception; visual completion; disocclusion; Bayesian model;relatability; Euler elastica
	Abstract	This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth. Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by minimizing the Euler's elastica as well as by incorporating the relatability of partially occluded contours and the convexity of the disoccluded objects. Then, to estimate the preferred scene we rely on a Bayesian model and define probabilities taking into account the global complexity of the objects in the hypothesized scenes as well as the effort of bringing these objects in their relative position in the planar image, which is also measured by an Euler's elastica-based quantity. The model is illustrated with numerical experiments on, both, synthetic and real images showing the ability of our model to reconstruct the occluded objects and the preferred perceptual order among them. We also present results on images of the Berkeley dataset with provided figure-ground ground-truth labeling.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; 601.235			Approved	no
	Call Number	Admin @ si @ OHD2016b			Serial	2745
Permanent link to this record



	Author	Javier Marin; David Vazquez; Antonio Lopez; Jaume Amores; Ludmila I. Kuncheva
	Title	Occlusion handling via random subspace classifiers for human detection			Type	Journal Article
	Year	2014	Publication	IEEE Transactions on Systems, Man, and Cybernetics (Part B)	Abbreviated Journal	TSMCB
	Volume	44	Issue	3	Pages	342-354
	Keywords	Pedestriand Detection; occlusion handling
	Abstract	This paper describes a general method to address partial occlusions for human detection in still images. The Random Subspace Method (RSM) is chosen for building a classifier ensemble robust against partial occlusions. The component classifiers are chosen on the basis of their individual and combined performance. The main contribution of this work lies in our approach’s capability to improve the detection rate when partial occlusions are present without compromising the detection performance on non occluded data. In contrast to many recent approaches, we propose a method which does not require manual labelling of body parts, defining any semantic spatial components, or using additional data coming from motion or stereo. Moreover, the method can be easily extended to other object classes. The experiments are performed on three large datasets: the INRIA person dataset, the Daimler Multicue dataset, and a new challenging dataset, called PobleSec, in which a considerable number of targets are partially occluded. The different approaches are evaluated at the classification and detection levels for both partially occluded and non-occluded data. The experimental results show that our detector outperforms state-of-the-art approaches in the presence of partial occlusions, while offering performance and reliability similar to those of the holistic approach on non-occluded data. The datasets used in our experiments have been made publicly available for benchmarking purposes
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	2168-2267	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS; 605.203; 600.057; 600.054; 601.042; 601.187; 600.076			Approved	no
	Call Number	ADAS @ adas @ MVL2014			Serial	2213
Permanent link to this record



	Author	Zhijie Fang; David Vazquez; Antonio Lopez
	Title	On-Board Detection of Pedestrian Intentions			Type	Journal Article
	Year	2017	Publication	Sensors	Abbreviated Journal	SENS
	Volume	17	Issue	10	Pages	2193
	Keywords	pedestrian intention; ADAS; self-driving
	Abstract	Avoiding vehicle-to-pedestrian crashes is a critical requirement for nowadays advanced driver assistant systems (ADAS) and future self-driving vehicles. Accordingly, detecting pedestrians from raw sensor data has a history of more than 15 years of research, with vision playing a central role. During the last years, deep learning has boosted the accuracy of image-based pedestrian detectors. However, detection is just the first step towards answering the core question, namely is the vehicle going to crash with a pedestrian provided preventive actions are not taken? Therefore, knowing as soon as possible if a detected pedestrian has the intention of crossing the road ahead of the vehicle is essential for performing safe and comfortable maneuvers that prevent a crash. However, compared to pedestrian detection, there is relatively little literature on detecting pedestrian intentions. This paper aims to contribute along this line by presenting a new vision-based approach which analyzes the pose of a pedestrian along several frames to determine if he or she is going to enter the road or not. We present experiments showing 750 ms of anticipation for pedestrians crossing the road, which at a typical urban driving speed of 50 km/h can provide 15 additional meters (compared to a pure pedestrian detector) for vehicle automatic reactions or to warn the driver. Moreover, in contrast with state-of-the-art methods, our approach is monocular, neither requiring stereo nor optical flow information.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS; 600.085; 600.076; 601.223; 600.116; 600.118			Approved	no
	Call Number	Admin @ si @ FVL2017			Serial	2983
Permanent link to this record



	Author	Alejandro Gonzalez Alzate; Zhijie Fang; Yainuvis Socarras; Joan Serrat; David Vazquez; Jiaolong Xu; Antonio Lopez
	Title	Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison			Type	Journal Article
	Year	2016	Publication	Sensors	Abbreviated Journal	SENS
	Volume	16	Issue	6	Pages	820
	Keywords	Pedestrian Detection; FIR
	Abstract	Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and night time. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images, (b) just infrared images and (c) both of them. In order to obtain results for the last item we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset we have built for this purpose as well as on the publicly available KAIST multispectral dataset.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1424-8220	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS; 600.085; 600.076; 600.082; 601.281			Approved	no
	Call Number	ADAS @ adas @ GFS2016			Serial	2754
Permanent link to this record



	Author	David Geronimo; Angel Sappa; Daniel Ponsa; Antonio Lopez
	Title	2D-3D based on-board pedestrian detection system			Type	Journal Article
	Year	2010	Publication	Computer Vision and Image Understanding	Abbreviated Journal	CVIU
	Volume	114	Issue	5	Pages	583–595
	Keywords	Pedestrian detection; Advanced Driver Assistance Systems; Horizon line; Haar wavelets; Edge orientation histograms
	Abstract	During the next decade, on-board pedestrian detection systems will play a key role in the challenge of increasing traffic safety. The main target of these systems, to detect pedestrians in urban scenarios, implies overcoming difficulties like processing outdoor scenes from a mobile platform and searching for aspect-changing objects in cluttered environments. This makes such systems combine techniques in the state-of-the-art Computer Vision. In this paper we present a three module system based on both 2D and 3D cues. The first module uses 3D information to estimate the road plane parameters and thus select a coherent set of regions of interest (ROIs) to be further analyzed. The second module uses Real AdaBoost and a combined set of Haar wavelets and edge orientation histograms to classify the incoming ROIs as pedestrian or non-pedestrian. The final module loops again with the 3D cue in order to verify the classified ROIs and with the 2D in order to refine the final results. According to the results, the integration of the proposed techniques gives rise to a promising system.
	Address	Computer Vision and Image Understanding (Special Issue on Intelligent Vision Systems), Vol. 114(5):583-595
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1077-3142	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	ADAS @ adas @ GSP2010			Serial	1341
Permanent link to this record



	Author	Muhammad Muzzamil Luqman; Jean-Yves Ramel; Josep Llados; Thierry Brouard
	Title	Fuzzy Multilevel Graph Embedding			Type	Journal Article
	Year	2013	Publication	Pattern Recognition	Abbreviated Journal	PR
	Volume	46	Issue	2	Pages	551-565
	Keywords	Pattern recognition; Graphics recognition; Graph clustering; Graph classification; Explicit graph embedding; Fuzzy logic
	Abstract	Structural pattern recognition approaches offer the most expressive, convenient, powerful but computational expensive representations of underlying relational information. To benefit from mature, less expensive and efficient state-of-the-art machine learning models of statistical pattern recognition they must be mapped to a low-dimensional vector space. Our method of explicit graph embedding bridges the gap between structural and statistical pattern recognition. We extract the topological, structural and attribute information from a graph and encode numeric details by fuzzy histograms and symbolic details by crisp histograms. The histograms are concatenated to achieve a simple and straightforward embedding of graph into a low-dimensional numeric feature vector. Experimentation on standard public graph datasets shows that our method outperforms the state-of-the-art methods of graph embedding for richly attributed graphs.
	Address
	Corporate Author				Thesis
	Publisher	Elsevier	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0031-3203	ISBN		Medium
	Area		Expedition		Conference
	Notes	DAG; 600.042; 600.045; 605.203			Approved	no
	Call Number	Admin @ si @ LRL2013a			Serial	2270
Permanent link to this record



	Author	Mariella Dimiccoli; Jean-Pascal Jacob; Lionel Moisan
	Title	Particle detection and tracking in fluorescence time-lapse imaging: a contrario approach			Type	Journal Article
	Year	2016	Publication	Journal of Machine Vision and Applications	Abbreviated Journal	MVAP
	Volume	27	Issue		Pages	511-527
	Keywords	particle detection; particle tracking; a-contrario approach; time-lapse fluorescence imaging
	Abstract	In this work, we propose a probabilistic approach for the detection and the tracking of particles on biological images. In presence of very noised and poor quality data, particles and trajectories can be characterized by an a-contrario model, that estimates the probability of observing the structures of interest in random data. This approach, first introduced in the modeling of human visual perception and then successfully applied in many image processing tasks, leads to algorithms that do not require a previous learning stage, nor a tedious parameter tuning and are very robust to noise. Comparative evaluations against a well established baseline show that the proposed approach outperforms the state of the art.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;			Approved	no
	Call Number	Admin @ si @ DJM2016			Serial	2735
Permanent link to this record



	Author	Mariella Dimiccoli; Benoît Girard; Alain Berthoz; Daniel Bennequin
	Title	Striola Magica: a functional explanation of otolith organs			Type	Journal Article
	Year	2013	Publication	Journal of Computational Neuroscience	Abbreviated Journal	JCN
	Volume	35	Issue	2	Pages	125-154
	Keywords	Otolith organs ;Striola; Vestibular pathway
	Abstract	Otolith end organs of vertebrates sense linear accelerations of the head and gravitation. The hair cells on their epithelia are responsible for transduction. In mammals, the striola, parallel to the line where hair cells reverse their polarization, is a narrow region centered on a curve with curvature and torsion. It has been shown that the striolar region is functionally different from the rest, being involved in a phasic vestibular pathway. We propose a mathematical and computational model that explains the necessity of this amazing geometry for the striola to be able to carry out its function. Our hypothesis, related to the biophysics of the hair cells and to the physiology of their afferent neurons, is that striolar afferents collect information from several type I hair cells to detect the jerk in a large domain of acceleration directions. This predicts a mean number of two calyces for afferent neurons, as measured in rodents. The domain of acceleration directions sensed by our striolar model is compatible with the experimental results obtained on monkeys considering all afferents. Therefore, the main result of our study is that phasic and tonic vestibular afferents cover the same geometrical fields, but at different dynamical and frequency domains.
	Address
	Corporate Author				Thesis
	Publisher	Springer US	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1573-6873. 2013	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB			Approved	no
	Call Number	Admin @ si @DBG2013			Serial	2787
Permanent link to this record



	Author	Katerine Diaz; Jesus Martinez del Rincon; Marçal Rusiñol; Aura Hernandez-Sabate
	Title	Feature Extraction by Using Dual-Generalized Discriminative Common Vectors			Type	Journal Article
	Year	2019	Publication	Journal of Mathematical Imaging and Vision	Abbreviated Journal	JMIV
	Volume	61	Issue	3	Pages	331-351
	Keywords	Online feature extraction; Generalized discriminative common vectors; Dual learning; Incremental learning; Decremental learning
	Abstract	In this paper, a dual online subspace-based learning method called dual-generalized discriminative common vectors (Dual-GDCV) is presented. The method extends incremental GDCV by exploiting simultaneously both the concepts of incremental and decremental learning for supervised feature extraction and classification. Our methodology is able to update the feature representation space without recalculating the full projection or accessing the previously processed training data. It allows both adding information and removing unnecessary data from a knowledge base in an efficient way, while retaining the previously acquired knowledge. The proposed method has been theoretically proved and empirically validated in six standard face recognition and classification datasets, under two scenarios: (1) removing and adding samples of existent classes, and (2) removing and adding new classes to a classification problem. Results show a considerable computational gain without compromising the accuracy of the model in comparison with both batch methodologies and other state-of-art adaptive methods.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	DAG; ADAS; 600.084; 600.118; 600.121; 600.129			Approved	no
	Call Number	Admin @ si @ DRR2019			Serial	3172
Permanent link to this record



	Author	Kai Wang; Joost Van de Weijer; Luis Herranz
	Title	ACAE-REMIND for online continual learning with compressed feature replay			Type	Journal Article
	Year	2021	Publication	Pattern Recognition Letters	Abbreviated Journal	PRL
	Volume	150	Issue		Pages	122-129
	Keywords	online continual learning; autoencoders; vector quantization
	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.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	LAMP; 600.147; 601.379; 600.120; 600.141			Approved	no
	Call Number	Admin @ si @ WWH2021			Serial	3575
Permanent link to this record