Home | [151–160] << 161 162 163 164 165 166 167 168 169 170 >> [171–180] |
Records | |||||
---|---|---|---|---|---|
Author | Joost Van de Weijer; Fahad Shahbaz Khan; Marc Masana | ||||
Title | Interactive Visual and Semantic Image Retrieval | Type | Book Chapter | ||
Year | 2013 | Publication | Multimodal Interaction in Image and Video Applications | Abbreviated Journal | |
Volume | 48 | Issue | Pages | 31-35 | |
Keywords | |||||
Abstract | 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. Wel apply a bagof- 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 image description to describe the composition and color scheme of the scene. Both descriptions are incorporated in a user feedback image retrieval setting. The main objective is to show that automatic labeling of images with semantic labels can improve image retrieval results. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer Berlin Heidelberg | Place of Publication | Editor | Angel Sappa; Jordi Vitria | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 1868-4394 | ISBN | 978-3-642-35931-6 | Medium | |
Area | Expedition | Conference | |||
Notes | CIC; 605.203; 600.048 | Approved | no | ||
Call Number | Admin @ si @ WKC2013 | Serial | 2284 | ||
Permanent link to this record | |||||
Author | Angel Morera; Angel Sanchez; Angel Sappa; Jose F. Velez | ||||
Title | Robust Detection of Outdoor Urban Advertising Panels in Static Images | Type | Conference Article | ||
Year | 2019 | Publication | 18th International Conference on Practical Applications of Agents and Multi-Agent Systems | Abbreviated Journal | |
Volume | Issue | Pages | 246-256 | ||
Keywords | Object detection; Urban ads panels; Deep learning; Single Shot Detector (SSD) architecture; Intersection over Union (IoU) metric; Augmented Reality | ||||
Abstract | One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images. | ||||
Address | Aquila; Italia; June 2019 | ||||
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 | PAAMS | ||
Notes | MSIAU; 600.130; 600.122 | Approved | no | ||
Call Number | Admin @ si @ MSS2019 | Serial | 3270 | ||
Permanent link to this record | |||||
Author | Yaxing Wang; Abel Gonzalez-Garcia; David Berga; Luis Herranz; Fahad Shahbaz Khan; Joost Van de Weijer | ||||
Title | MineGAN: effective knowledge transfer from GANs to target domains with few images | Type | Conference Article | ||
Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. This property has been extensively studied for discriminative networks but has received significantly less attention for generative models. Given the often enormous effort required to train GANs, both computationally as well as in the dataset collection, the re-use of pretrained GANs is a desirable objective. We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods such as mode collapse and lack of flexibility. We perform experiments on several complex datasets using various GAN architectures (BigGAN, Progressive GAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. | ||||
Address | Virtual CVPR | ||||
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 | CVPR | ||
Notes | LAMP; 600.109; 600.141; 600.120 | Approved | no | ||
Call Number | Admin @ si @ WGB2020 | Serial | 3421 | ||
Permanent link to this record | |||||
Author | Jorge Bernal | ||||
Title | Use of Projection and Back-projection Methods in Bidimensional Computed Tomography Image Reconstruction | Type | Report | ||
Year | 2009 | Publication | CVC Tecnical Report | Abbreviated Journal | |
Volume | 141 | Issue | Pages | ||
Keywords | Projection, Back-projection, CT scan, Euclidean geometry, Radon transform | ||||
Abstract | One of the biggest drawbacks related to the use of CT scanners is the cost (in memory and in time) associated. In this project many methods to simulate their functioning, but in a more feasible way (taking an industrial point of view), will be studied.
The main group of techniques that are being used are the one entitled as ’back-projection’. The concept behind is to simulate the X ray emission in CT scans by lines that cross with the image we want to reconstruct. In the first part of this document euclidean geometry is used to face the tasks of projec- tion and back-projection. After analysing the results achieved it has been proved that this approach does not lead to a fully perfect reconstruction (and also has some other problems related to running time and memory cost). Because of this in the second part of the document ’Filtered Back-projection’ method is introduced in order to improve the results. Filtered Back-projection methods rely on mathematical transforms (Fourier, Radon) in order to provide more accurate results that can be obtained in much less time. The main cause of this better results is the use of a filtering process before the back-projection in order to avoid high frequency-caused errors. As a result of this project two different implementations (one for each approach) had been implemented in order to compare their performance. |
||||
Address | |||||
Corporate Author | Computer Vision Center | Thesis | Master's thesis | ||
Publisher | Place of Publication | Barcelona, Spain | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | 800 | Expedition | Conference | ||
Notes | MV; | Approved | no | ||
Call Number | IAM @ iam @ Ber2009 | Serial | 1693 | ||
Permanent link to this record | |||||
Author | Razieh Rastgoo; Kourosh Kiani; Sergio Escalera | ||||
Title | Real-time Isolated Hand Sign Language RecognitioN Using Deep Networks and SVD | Type | Journal | ||
Year | 2022 | Publication | Journal of Ambient Intelligence and Humanized Computing | Abbreviated Journal | |
Volume | 13 | Issue | Pages | 591–611 | |
Keywords | |||||
Abstract | One of the challenges in computer vision models, especially sign language, is real-time recognition. In this work, we present a simple yet low-complex and efficient model, comprising single shot detector, 2D convolutional neural network, singular value decomposition (SVD), and long short term memory, to real-time isolated hand sign language recognition (IHSLR) from RGB video. We employ the SVD method as an efficient, compact, and discriminative feature extractor from the estimated 3D hand keypoints coordinators. Despite the previous works that employ the estimated 3D hand keypoints coordinates as raw features, we propose a novel and revolutionary way to apply the SVD to the estimated 3D hand keypoints coordinates to get more discriminative features. SVD method is also applied to the geometric relations between the consecutive segments of each finger in each hand and also the angles between these sections. We perform a detailed analysis of recognition time and accuracy. One of our contributions is that this is the first time that the SVD method is applied to the hand pose parameters. Results on four datasets, RKS-PERSIANSIGN (99.5±0.04), First-Person (91±0.06), ASVID (93±0.05), and isoGD (86.1±0.04), confirm the efficiency of our method in both accuracy (mean+std) and time recognition. Furthermore, our model outperforms or gets competitive results with the state-of-the-art alternatives in IHSLR and hand action recognition. | ||||
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 | HUPBA; no proj | Approved | no | ||
Call Number | Admin @ si @ RKE2022a | Serial | 3660 | ||
Permanent link to this record | |||||
Author | Jorge Bernal; F. Javier Sanchez; Fernando Vilariño | ||||
Title | Reduction of Pattern Search Area in Colonoscopy Images by Merging Non-Informative Regions | Type | Conference Article | ||
Year | 2010 | Publication | 28th Congreso Anual de la Sociedad Española de Ingeniería Biomédica | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | One of the first usual steps in pattern recognition schemas is image segmentation, in order to reduce the dimensionality of the problem and manage smaller quantity of data. In our case as we are pursuing real-time colon cancer polyp detection, this step is crucial. In this paper we present a non-informative region estimation algorithm that will let us discard some parts of the image where we will not expect to find colon cancer polyps. The performance of our approach will be measured in terms of both non-informative areas elimination and polyps’ areas preserving. The results obtained show the importance of having correct non- informative region estimation in order to fasten the whole recognition process. | ||||
Address | Madrid (Spain) | ||||
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 | 800 | Expedition | Conference | CASEIB | |
Notes | MV;SIAI | Approved | no | ||
Call Number | Admin @ si @ BSV2010 | Serial | 1469 | ||
Permanent link to this record | |||||
Author | Lu Yu | ||||
Title | Semantic Representation: From Color to Deep Embeddings | Type | Book Whole | ||
Year | 2019 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | One of the fundamental problems of computer vision is to represent images with compact semantically relevant embeddings. These embeddings could then be used in a wide variety of applications, such as image retrieval, object detection, and video search. The main objective of this thesis is to study image embeddings from two aspects: color embeddings and deep embeddings.
In the first part of the thesis we start from hand-crafted color embeddings. We propose a method to order the additional color names according to their complementary nature with the basic eleven color names. This allows us to compute color name representations with high discriminative power of arbitrary length. Psychophysical experiments confirm that our proposed method outperforms baseline approaches. Secondly, we learn deep color embeddings from weakly labeled data by adding an attention strategy. The attention branch is able to correctly identify the relevant regions for each class. The advantage of our approach is that it can learn color names for specific domains for which no pixel-wise labels exists. In the second part of the thesis, we focus on deep embeddings. Firstly, we address the problem of compressing large embedding networks into small networks, while maintaining similar performance. We propose to distillate the metrics from a teacher network to a student network. Two new losses are introduced to model the communication of a deep teacher network to a small student network: one based on an absolute teacher, where the student aims to produce the same embeddings as the teacher, and one based on a relative teacher, where the distances between pairs of data points is communicated from the teacher to the student. In addition, various aspects of distillation have been investigated for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. Finally, another aspect of deep metric learning, namely lifelong learning, is studied. We observed some drift occurs during training of new tasks for metric learning. A method to estimate the semantic drift based on the drift which is experienced by data of the current task during its training is introduced. Having this estimation, previous tasks can be compensated for this drift, thereby improving their performance. Furthermore, we show that embedding networks suffer significantly less from catastrophic forgetting compared to classification networks when learning new tasks. |
||||
Address | November 2019 | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Joost Van de Weijer;Yongmei Cheng | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-121011-3-3 | Medium | ||
Area | Expedition | Conference | |||
Notes | LAMP; 600.120 | Approved | no | ||
Call Number | Admin @ si @ Yu2019 | Serial | 3394 | ||
Permanent link to this record | |||||
Author | Aymen Azaza; Joost Van de Weijer; Ali Douik; Marc Masana | ||||
Title | Context Proposals for Saliency Detection | Type | Journal Article | ||
Year | 2018 | Publication | Computer Vision and Image Understanding | Abbreviated Journal | CVIU |
Volume | 174 | Issue | Pages | 1-11 | |
Keywords | |||||
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). |
||||
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; 600.109; 600.120 | Approved | no | ||
Call Number | Admin @ si @ AWD2018 | Serial | 3241 | ||
Permanent link to this record | |||||
Author | Margarita Torre; Beatriz Remeseiro; Petia Radeva; Fernando Martinez | ||||
Title | DeepNEM: Deep Network Energy-Minimization for Agricultural Field Segmentation | Type | Journal Article | ||
Year | 2020 | Publication | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | Abbreviated Journal | JSTAEOR |
Volume | 13 | Issue | Pages | 726-737 | |
Keywords | |||||
Abstract | One of the main characteristics of agricultural fields is that the appearance of different crops and their growth status, in an aerial image, is varied, and has a wide range of radiometric values and high level of variability. The extraction of these fields and their monitoring are activities that require a high level of human intervention. In this article, we propose a novel automatic algorithm, named deep network energy-minimization (DeepNEM), to extract agricultural fields in aerial images. The model-guided process selects the most relevant image clues extracted by a deep network, completes them and finally generates regions that represent the agricultural fields under a minimization scheme. DeepNEM has been tested over a broad range of fields in terms of size, shape, and content. Different measures were used to compare the DeepNEM with other methods, and to prove that it represents an improved approach to achieve a high-quality segmentation of agricultural fields. Furthermore, this article also presents a new public dataset composed of 1200 images with their parcels boundaries annotations. | ||||
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 @ TRR2020 | Serial | 3410 | ||
Permanent link to this record | |||||
Author | Alicia Fornes; Josep Llados; Gemma Sanchez; Dimosthenis Karatzas | ||||
Title | Rotation Invariant Hand-Drawn Symbol Recognition based on a Dynamic Time Warping Model | Type | Journal Article | ||
Year | 2010 | Publication | International Journal on Document Analysis and Recognition | Abbreviated Journal | IJDAR |
Volume | 13 | Issue | 3 | Pages | 229–241 |
Keywords | |||||
Abstract | One of the major difficulties of handwriting symbol recognition is the high variability among symbols because of the different writer styles. In this paper, we introduce a robust approach for describing and recognizing hand-drawn symbols tolerant to these writer style differences. This method, which is invariant to scale and rotation, is based on the dynamic time warping (DTW) algorithm. The symbols are described by vector sequences, a variation of the DTW distance is used for computing the matching distance, and K-Nearest Neighbor is used to classify them. Our approach has been evaluated in two benchmarking scenarios consisting of hand-drawn symbols. Compared with state-of-the-art methods for symbol recognition, our method shows higher tolerance to the irregular deformations induced by hand-drawn strokes. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer-Verlag | 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; IF 2009: 1,213 | Approved | no | ||
Call Number | DAG @ dag @ FLS2010a | Serial | 1288 | ||
Permanent link to this record | |||||
Author | Sanket Biswas; Pau Riba; Josep Llados; Umapada Pal | ||||
Title | Graph-Based Deep Generative Modelling for Document Layout Generation | Type | Conference Article | ||
Year | 2021 | Publication | 16th International Conference on Document Analysis and Recognition | Abbreviated Journal | |
Volume | 12917 | Issue | Pages | 525-537 | |
Keywords | |||||
Abstract | One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable and plausible document layouts that can be used to train document interpretation systems, in this case, specially in digital mailroom applications. It is also the first graph-based approach for document layout generation task experimented on administrative document images, in this case, invoices. | ||||
Address | Lausanne; Suissa; September 2021 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG; 600.121; 600.140; 110.312 | Approved | no | ||
Call Number | Admin @ si @ BRL2021 | Serial | 3676 | ||
Permanent link to this record | |||||
Author | Sergio Escalera; Oriol Pujol; Petia Radeva | ||||
Title | Recoding Error-Correcting Output Codes | Type | Conference Article | ||
Year | 2009 | Publication | 8th International Workshop of Multiple Classifier Systems | Abbreviated Journal | |
Volume | 5519 | Issue | Pages | 11–21 | |
Keywords | |||||
Abstract | One of the most widely applied techniques to deal with multi- class categorization problems is the pairwise voting procedure. Recently, this classical approach has been embedded in the Error-Correcting Output Codes framework (ECOC). This framework is based on a coding step, where a set of binary problems are learnt and coded in a matrix, and a decoding step, where a new sample is tested and classified according to a comparison with the positions of the coded matrix. In this paper, we present a novel approach to redefine without retraining, in a problem-dependent way, the one-versus-one coding matrix so that the new coded information increases the generalization capability of the system. Moreover, the final classification can be tuned with the inclusion of a weighting matrix in the decoding step. The approach has been validated over several UCI Machine Learning repository data sets and two real multi-class problems: traffic sign and face categorization. The results show that performance improvements are obtained when comparing the new approach to one of the best ECOC designs (one-versus-one). Furthermore, the novel methodology obtains at least the same performance than the one-versus-one ECOC design. | ||||
Address | Reykjavik (Iceland) | ||||
Corporate Author | Thesis | ||||
Publisher | Springer Berlin Heidelberg | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0302-9743 | ISBN | 978-3-642-02325-5 | Medium | |
Area | Expedition | Conference | MCS | ||
Notes | MILAB;HuPBA | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ EPR2009d | Serial | 1190 | ||
Permanent link to this record | |||||
Author | Oriol Pujol; Eloi Puertas; Carlo Gatta | ||||
Title | Multi-scale Stacked Sequential Learning | Type | Conference Article | ||
Year | 2009 | Publication | 8th International Workshop of Multiple Classifier Systems | Abbreviated Journal | |
Volume | 5519 | Issue | Pages | 262–271 | |
Keywords | |||||
Abstract | One of the most widely used assumptions in supervised learning is that data is independent and identically distributed. This assumption does not hold true in many real cases. Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring examples exhibit some kind of relationship. In the literature, there are different approaches that try to capture and exploit this correlation, by means of different methodologies. In this paper we focus on meta-learning strategies and, in particular, the stacked sequential learning approach. The main contribution of this work is two-fold: first, we generalize the stacked sequential learning. This generalization reflects the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions by means of a multi-scale pyramidal decomposition of the predicted labels. Additionally, this new method subsumes the standard stacked sequential learning approach. We tested the proposed method on two different classification tasks: text lines classification in a FAQ data set and image classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning. Moreover, we show that the proposed method allows to control the trade-off between the detail and the desired range of the interactions. | ||||
Address | Reykjavik, Iceland | ||||
Corporate Author | Thesis | ||||
Publisher | Springer Berlin Heidelberg | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0302-9743 | ISBN | 978-3-642-02325-5 | Medium | |
Area | Expedition | Conference | MCS | ||
Notes | MILAB;HuPBA | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ PPG2009 | Serial | 1260 | ||
Permanent link to this record | |||||
Author | Carlo Gatta; Eloi Puertas; Oriol Pujol | ||||
Title | Multi-Scale Stacked Sequential Learning | Type | Journal Article | ||
Year | 2011 | Publication | Pattern Recognition | Abbreviated Journal | PR |
Volume | 44 | Issue | 10-11 | Pages | 2414-2416 |
Keywords | Stacked sequential learning; Multiscale; Multiresolution; Contextual classification | ||||
Abstract | One of the most widely used assumptions in supervised learning is that data is independent and identically distributed. This assumption does not hold true in many real cases. Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring examples exhibit some kind of relationship. In the literature, there are different approaches that try to capture and exploit this correlation, by means of different methodologies. In this paper we focus on meta-learning strategies and, in particular, the stacked sequential learning approach. The main contribution of this work is two-fold: first, we generalize the stacked sequential learning. This generalization reflects the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions by means of a multi-scale pyramidal decomposition of the predicted labels. Additionally, this new method subsumes the standard stacked sequential learning approach. We tested the proposed method on two different classification tasks: text lines classification in a FAQ data set and image classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning. Moreover, we show that the proposed method allows to control the trade-off between the detail and the desired range of the interactions. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | MILAB;HuPBA | Approved | no | ||
Call Number | Admin @ si @ GPP2011 | Serial | 1802 | ||
Permanent link to this record | |||||
Author | Albin Soutif; Antonio Carta; Andrea Cossu; Julio Hurtado; Hamed Hemati; Vincenzo Lomonaco; Joost Van de Weijer | ||||
Title | A Comprehensive Empirical Evaluation on Online Continual Learning | Type | Conference Article | ||
Year | 2023 | Publication | Visual Continual Learning (ICCV-W) | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical evaluation, we evaluate various methods from the literature that tackle online continual learning. More specifically, we focus on the class-incremental setting in the context of image classification, where the learner must learn new classes incrementally from a stream of data. We compare these methods on the Split-CIFAR100 and Split-TinyImagenet benchmarks, and measure their average accuracy, forgetting, stability, and quality of the representations, to evaluate various aspects of the algorithm at the end but also during the whole training period. We find that most methods suffer from stability and underfitting issues. However, the learned representations are comparable to i.i.d. training under the same computational budget. No clear winner emerges from the results and basic experience replay, when properly tuned and implemented, is a very strong baseline. We release our modular and extensible codebase at this https URL based on the avalanche framework to reproduce our results and encourage future research. | ||||
Address | Paris; France; October 2023 | ||||
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 | ICCVW | ||
Notes | LAMP | Approved | no | ||
Call Number | Admin @ si @ SCC2023 | Serial | 3938 | ||
Permanent link to this record |