Home [201–210] << 211 212 213 214 215 216 217 218 219 220 >> [221–228]
List View
 | 
Citations
 | 
Details
   web
Records
Author Wenjuan Gong; Y.Huang; Jordi Gonzalez; Liang Wang
Title An Effective Solution to Double Counting Problem in Human Pose Estimation Type Miscellaneous
Year 2015 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords (up) Pose estimation; double counting problem; mix-ture of parts Model
Abstract The mixture of parts model has been successfully applied to solve the 2D
human pose estimation problem either as an explicitly trained body part model
or as latent variables for pedestrian detection. Even in the era of massive
applications of deep learning techniques, the mixture of parts model is still
effective in solving certain problems, especially in the case with limited
numbers of training samples. In this paper, we consider using the mixture of
parts model for pose estimation, wherein a tree structure is utilized for
representing relations between connected body parts. This strategy facilitates
training and inferencing of the model but suffers from double counting
problems, where one detected body part is counted twice due to lack of
constrains among unconnected body parts. To solve this problem, we propose a
generalized solution in which various part attributes are captured by multiple
features so as to avoid the double counted problem. Qualitative and
quantitative experimental results on a public available dataset demonstrate the
effectiveness of our proposed method.

An Effective Solution to Double Counting Problem in Human Pose Estimation – ResearchGate. Available from: http://www.researchgate.net/publication/271218491AnEffectiveSolutiontoDoubleCountingProbleminHumanPose_Estimation [accessed Oct 22, 2015].
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 ISE; 600.078 Approved no
Call Number Admin @ si @ GHG2015 Serial 2590
Permanent link to this record
 
 
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 (up) 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 Laura Igual; Xavier Perez Sala; Sergio Escalera; Cecilio Angulo; Fernando De la Torre
Title Continuous Generalized Procrustes Analysis Type Journal Article
Year 2014 Publication Pattern Recognition Abbreviated Journal PR
Volume 47 Issue 2 Pages 659–671
Keywords (up) Procrustes analysis; 2D shape model; Continuous approach
Abstract PR4883, PII: S0031-3203(13)00327-0
Two-dimensional shape models have been successfully applied to solve many problems in computer vision, such as object tracking, recognition, and segmentation. Typically, 2D shape models are learned from a discrete set of image landmarks (corresponding to projection of 3D points of an object), after applying Generalized Procustes Analysis (GPA) to remove 2D rigid transformations. However, the
standard GPA process suffers from three main limitations. Firstly, the 2D training samples do not necessarily cover a uniform sampling of all the 3D transformations of an object. This can bias the estimate of the shape model. Secondly, it can be computationally expensive to learn the shape model by sampling 3D transformations. Thirdly, standard GPA methods use only one reference shape, which can might be insufficient to capture large structural variability of some objects.
To address these drawbacks, this paper proposes continuous generalized Procrustes analysis (CGPA).
CGPA uses a continuous formulation that avoids the need to generate 2D projections from all the rigid 3D transformations. It builds an efficient (in space and time) non-biased 2D shape model from a set of 3D model of objects. A major challenge in CGPA is the need to integrate over the space of 3D rotations, especially when the rotations are parameterized with Euler angles. To address this problem, we introduce the use of the Haar measure. Finally, we extended CGPA to incorporate several reference shapes. Experimental results on synthetic and real experiments show the benefits of CGPA over GPA.
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 OR; HuPBA; 605.203; 600.046;MILAB Approved no
Call Number Admin @ si @ IPE2014 Serial 2352
Permanent link to this record
 
 
Author Anjan Dutta; Josep Llados; Horst Bunke; Umapada Pal
Title A Product Graph Based Method for Dual Subgraph Matching Applied to Symbol Spotting Type Book Chapter
Year 2014 Publication Graphics Recognition. Current Trends and Challenges Abbreviated Journal
Volume 8746 Issue Pages 7-11
Keywords (up) Product graph; Dual edge graph; Subgraph matching; Random walks; Graph kernel
Abstract Product graph has been shown as a way for matching subgraphs. This paper reports the extension of the product graph methodology for subgraph matching applied to symbol spotting in graphical documents. Here we focus on the two major limitations of the previous version of the algorithm: (1) spurious nodes and edges in the graph representation and (2) inefficient node and edge attributes. To deal with noisy information of vectorized graphical documents, we consider a dual edge graph representation on the original graph representing the graphical information and the product graph is computed between the dual edge graphs of the pattern graph and the target graph. The dual edge graph with redundant edges is helpful for efficient and tolerating encoding of the structural information of the graphical documents. The adjacency matrix of the product graph locates the pair of similar edges of two operand graphs and exponentiating the adjacency matrix finds similar random walks of greater lengths. Nodes joining similar random walks between two graphs are found by combining different weighted exponentials of adjacency matrices. An experimental investigation reveals that the recall obtained by this approach is quite encouraging.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor Bart Lamiroy; Jean-Marc Ogier
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-662-44853-3 Medium
Area Expedition Conference
Notes DAG; 600.077 Approved no
Call Number Admin @ si @ DLB2014 Serial 2698
Permanent link to this record
 
 
Author Enric Marti; Debora Gil; Carme Julia
Title A PBL experience in the teaching of Computer Graphics Type Conference Article
Year 2005 Publication EUROGRAPHICS Proceedings Abbreviated Journal
Volume 5 Issue 1 Pages 95-103
Keywords (up) project-based learning; computer graphics education; Open GL; rendering techniques; computer animation techniques; Graphics packages; Hierarchy and geometric transformations; Animation; Color; shading; shadowing and texture; fractals; hidden line/surface removal; Problem Based Learning
Abstract Project-Based Learning (PBL) is an educational strategy to improve student’s learning capability that, in recent years, has had a progressive acceptance in undergraduate studies. This methodology is based on solving a problem or project in a student working group. In this way, PBL focuses on learning the necessary tools to correctly find a solution to given problems. Since the learning initiative is transferred to the student, the PBL method promotes students own abilities. This allows a better assessment of the true workload that carries out the student in the subject. It follows that the methodology conforms to the guidelines of the Bologna document, which quantifies the student workload in a subject by means of the European credit transfer system (ECTS). PBL is currently applied in undergraduate studies needing strong practical training such as medicine, nursing or law sciences. Although this is also the case in engineering studies, amazingly, few experiences have been reported. In this paper we propose to use PBL in the educational organization of the Computer Graphics subjects in the Computer Science degree. Our PBL project focuses in the development of a C++ graphical environment based on the OpenGL libraries for visualization and handling of different graphical objects. The starting point is a basic skeleton that already includes lighting functions, perspective projection with mouse interaction to change the point of view and three predefined objects. Students have to complete this skeleton by adding their own functions to solve the project. A total number of 10 projects have been proposed and successfully solved. The exercises range from human face rendering to articulated objects, such as robot arms or puppets. In the present paper we extensively report the statement and educational objectives for two of the projects: solar system visualization and a chess game. We report our earlier educational experience based on the standard classroom theoretical, problem and practice sessions and the reasons that motivated searching for other learning methods. We have mainly chosen PBL because it improves the student learning initiative. We have applied the PBL educational model since the beginning of the second semester. The student’s feedback increases in his interest for the subject. We present a comparative study of the teachers’ and students’ workload between PBL and the classic teaching approach, which suggests that the workload increase in PBL is not as high as it seems.
Address Dublin; Ireland; September 2005
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 EUROGRAPHICS
Notes IAM;ADAS; Approved no
Call Number IAM @ iam @ MGJ2005 Serial 1593
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 (up) 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 Aleksandr Setkov; Fabio Martinez Carillo; Michele Gouiffes; Christian Jacquemin; Maria Vanrell; Ramon Baldrich
Title DAcImPro: A Novel Database of Acquired Image Projections and Its Application to Object Recognition Type Conference Article
Year 2015 Publication Advances in Visual Computing. Proceedings of 11th International Symposium, ISVC 2015 Part II Abbreviated Journal
Volume 9475 Issue Pages 463-473
Keywords (up) Projector-camera systems; Feature descriptors; Object recognition
Abstract Projector-camera systems are designed to improve the projection quality by comparing original images with their captured projections, which is usually complicated due to high photometric and geometric variations. Many research works address this problem using their own test data which makes it extremely difficult to compare different proposals. This paper has two main contributions. Firstly, we introduce a new database of acquired image projections (DAcImPro) that, covering photometric and geometric conditions and providing data for ground-truth computation, can serve to evaluate different algorithms in projector-camera systems. Secondly, a new object recognition scenario from acquired projections is presented, which could be of a great interest in such domains, as home video projections and public presentations. We show that the task is more challenging than the classical recognition problem and thus requires additional pre-processing, such as color compensation or projection area selection.
Address
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-319-27862-9 Medium
Area Expedition Conference ISVC
Notes CIC Approved no
Call Number Admin @ si @ SMG2015 Serial 2736
Permanent link to this record
 
 
Author Abel Gonzalez-Garcia; Davide Modolo; Vittorio Ferrari
Title Objects as context for detecting their semantic parts Type Conference Article
Year 2018 Publication 31st IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages 6907 - 6916
Keywords (up) Proposals; Semantics; Wheels; Automobiles; Context modeling; Task analysis; Object detection
Abstract We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to
detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compare
to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.
Address Salt Lake City; USA; June 2018
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; 600.120 Approved no
Call Number Admin @ si @ GMF2018 Serial 3229
Permanent link to this record
 
 
Author Qingshan Chen; Zhenzhen Quan; Yujun Li; Chao Zhai; Mikhail Mozerov
Title An Unsupervised Domain Adaption Approach for Cross-Modality RGB-Infrared Person Re-Identification Type Journal Article
Year 2023 Publication IEEE Sensors Journal Abbreviated Journal IEEE-SENS
Volume 23 Issue 24 Pages
Keywords (up) Q. Chen, Z. Quan, Y. Li, C. Zhai and M. G. Mozerov
Abstract Dual-camera systems commonly employed in surveillance serve as the foundation for RGB-infrared (IR) cross-modality person re-identification (ReID). However, significant modality differences give rise to inferior performance compared to single-modality scenarios. Furthermore, most existing studies in this area rely on supervised training with meticulously labeled datasets. Labeling RGB-IR image pairs is more complex than labeling conventional image data, and deploying pretrained models on unlabeled datasets can lead to catastrophic performance degradation. In contrast to previous solutions that focus solely on cross-modality or domain adaptation issues, this article presents an end-to-end unsupervised domain adaptation (UDA) framework for the cross-modality person ReID, which can simultaneously address both of these challenges. This model employs source domain classes, target domain clusters, and unclustered instance samples for the training, maximizing the comprehensive use of the dataset. Moreover, it addresses the problem of mismatched clustering labels between the two modalities in the target domain by incorporating a label matching module that reassigns reliable clusters with labels, ensuring correspondence between different modality labels. We construct the loss function by incorporating distinctiveness loss and multiplicity loss, both of which are determined by the similarity of neighboring features in the predicted feature space and the difference between distant features. This approach enables efficient feature clustering and cluster class assignment to occur concurrently. Eight UDA cross-modality person ReID experiments are conducted on three real datasets and six synthetic datasets. The experimental results unequivocally demonstrate that the proposed model outperforms the existing state-of-the-art algorithms to a significant degree. Notably, in RegDB → RegDB_light, the Rank-1 accuracy exhibits a remarkable improvement of 8.24%.
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 Approved no
Call Number Admin @ si @ CQL2023 Serial 3884
Permanent link to this record
 
 
Author Xavier Carrillo; E Fernandez-Nofrerias; Francesco Ciompi; Oriol Rodriguez-Leor; Petia Radeva; Neus Salvatella; Oriol Pujol; J. Mauri; A. Bayes
Title Changes in Radial Artery Volume Assessed Using Intravascular Ultrasound: A Comparison of Two Vasodilator Regimens in Transradial Coronary Intervention Type Journal Article
Year 2011 Publication Journal of Invasive Cardiology Abbreviated Journal JOIC
Volume 23 Issue 10 Pages 401-404
Keywords (up) radial; vasodilator treatment; percutaneous coronary intervention; IVUS; volumetric IVUS analysis
Abstract OBJECTIVES:
This study used intravascular ultrasound (IVUS) to evaluate radial artery volume changes after intraarterial administration of nitroglycerin and/or verapamil.
BACKGROUND:
Radial artery spasm, which is associated with radial artery size, is the main limitation of the transradial approach in percutaneous coronary interventions (PCI).
METHODS:
This prospective, randomized study compared the effect of two intra-arterial vasodilator regimens on radial artery volume: 0.2 mg of nitroglycerin plus 2.5 mg of verapamil (Group 1; n = 15) versus 2.5 mg of verapamil alone (Group 2; n = 15). Radial artery lumen volume was assessed using IVUS at two time points: at baseline (5 minutes after sheath insertion) and post-vasodilator (1 minute after drug administration). The luminal volume of the radial artery was computed using ECOC Random Fields (ECOC-RF), a technique used for automatic segmentation of luminal borders in longitudinal cut images from IVUS sequences.
RESULTS:
There was a significant increase in arterial lumen volume in both groups, with an increase from 451 ± 177 mm³ to 508 ± 192 mm³ (p = 0.001) in Group 1 and from 456 ± 188 mm³ to 509 ± 170 mm³ (p = 0.001) in Group 2. There were no significant differences between the groups in terms of absolute volume increase (58 mm³ versus 53 mm³, respectively; p = 0.65) or in relative volume increase (14% versus 20%, respectively; p = 0.69).
CONCLUSIONS:
Administration of nitroglycerin plus verapamil or verapamil alone to the radial artery resulted in similar increases in arterial lumen volume according to ECOC-RF IVUS measurements.
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;HuPBA Approved no
Call Number Admin @ si @ CFC2011 Serial 1797
Permanent link to this record
 
 
Author Chris Bahnsen; David Vazquez; Antonio Lopez; Thomas B. Moeslund
Title Learning to Remove Rain in Traffic Surveillance by Using Synthetic Data Type Conference Article
Year 2019 Publication 14th International Conference on Computer Vision Theory and Applications Abbreviated Journal
Volume Issue Pages 123-130
Keywords (up) Rain Removal; Traffic Surveillance; Image Denoising
Abstract Rainfall is a problem in automated traffic surveillance. Rain streaks occlude the road users and degrade the overall visibility which in turn decrease object detection performance. One way of alleviating this is by artificially removing the rain from the images. This requires knowledge of corresponding rainy and rain-free images. Such images are often produced by overlaying synthetic rain on top of rain-free images. However, this method fails to incorporate the fact that rain fall in the entire three-dimensional volume of the scene. To overcome this, we introduce training data from the SYNTHIA virtual world that models rain streaks in the entirety of a scene. We train a conditional Generative Adversarial Network for rain removal and apply it on traffic surveillance images from SYNTHIA and the AAU RainSnow datasets. To measure the applicability of the rain-removed images in a traffic surveillance context, we run the YOLOv2 object detection algorithm on the original and rain-removed frames. The results on SYNTHIA show an 8% increase in detection accuracy compared to the original rain image. Interestingly, we find that high PSNR or SSIM scores do not imply good object detection performance.
Address Praga; Czech Republic; February 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 VISIGRAPP
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ BVL2019 Serial 3256
Permanent link to this record
 
 
Author Svebor Karaman; Giuseppe Lisanti; Andrew Bagdanov; Alberto del Bimbo
Title Leveraging local neighborhood topology for large scale person re-identification Type Journal Article
Year 2014 Publication Pattern Recognition Abbreviated Journal PR
Volume 47 Issue 12 Pages 3767–3778
Keywords (up) Re-identification; Conditional random field; Semi-supervised; ETHZ; CAVIAR; 3DPeS; CMV100
Abstract In this paper we describe a semi-supervised approach to person re-identification that combines discriminative models of person identity with a Conditional Random Field (CRF) to exploit the local manifold approximation induced by the nearest neighbor graph in feature space. The linear discriminative models learned on few gallery images provides coarse separation of probe images into identities, while a graph topology defined by distances between all person images in feature space leverages local support for label propagation in the CRF. We evaluate our approach using multiple scenarios on several publicly available datasets, where the number of identities varies from 28 to 191 and the number of images ranges between 1003 and 36 171. We demonstrate that the discriminative model and the CRF are complementary and that the combination of both leads to significant improvement over state-of-the-art approaches. We further demonstrate how the performance of our approach improves with increasing test data and also with increasing amounts of additional unlabeled data.
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; 601.240; 600.079 Approved no
Call Number Admin @ si @ KLB2014a Serial 2522
Permanent link to this record
 
 
Author Svebor Karaman; Giuseppe Lisanti; Andrew Bagdanov; Alberto del Bimbo
Title From re-identification to identity inference: Labeling consistency by local similarity constraints Type Book Chapter
Year 2014 Publication Person Re-Identification Abbreviated Journal
Volume 2 Issue Pages 287-307
Keywords (up) re-identification; Identity inference; Conditional random fields; Video surveillance
Abstract In this chapter, we introduce the problem of identity inference as a generalization of person re-identification. It is most appropriate to distinguish identity inference from re-identification in situations where a large number of observations must be identified without knowing a priori that groups of test images represent the same individual. The standard single- and multishot person re-identification common in the literature are special cases of our formulation. We present an approach to solving identity inference by modeling it as a labeling problem in a Conditional Random Field (CRF). The CRF model ensures that the final labeling gives similar labels to detections that are similar in feature space. Experimental results are given on the ETHZ, i-LIDS and CAVIAR datasets. Our approach yields state-of-the-art performance for multishot re-identification, and our results on the more general identity inference problem demonstrate that we are able to infer the identity of very many examples even with very few labeled images in the gallery.
Address
Corporate Author Thesis
Publisher Springer London Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2191-6586 ISBN 978-1-4471-6295-7 Medium
Area Expedition Conference
Notes LAMP; 600.079 Approved no
Call Number Admin @ si @KLB2014b Serial 2521
Permanent link to this record
 
 
Author Diego Velazquez; Pau Rodriguez; Josep M. Gonfaus; Xavier Roca; Jordi Gonzalez
Title A Closer Look at Embedding Propagation for Manifold Smoothing Type Journal Article
Year 2022 Publication Journal of Machine Learning Research Abbreviated Journal JMLR
Volume 23 Issue 252 Pages 1-27
Keywords (up) Regularization; emi-supervised learning; self-supervised learning; adversarial robustness; few-shot classification
Abstract Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be sensitive to out-of-distribution (OOD) data.
Self- and semi-supervised training schemes reduce the amount of annotated data required during the training process. However, OOD generalization remains a major challenge for most methods. Strategies that promote smoother decision boundaries play an important role in out-of-distribution generalization. For example, embedding propagation (EP) for manifold smoothing has recently shown to considerably improve the OOD performance for few-shot classification. EP achieves smoother class manifolds by building a graph from sample embeddings and propagating information through the nodes in an unsupervised manner. In this work, we extend the original EP paper providing additional evidence and experiments showing that it attains smoother class embedding manifolds and improves results in settings beyond few-shot classification. Concretely, we show that EP improves the robustness of neural networks against multiple adversarial attacks as well as semi- and
self-supervised learning performance.
Address 9/2022
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 Approved no
Call Number Admin @ si @ VRG2022 Serial 3762
Permanent link to this record
 
 
Author Monica Piñol; Angel Sappa; Ricardo Toledo
Title Adaptive Feature Descriptor Selection based on a Multi-Table Reinforcement Learning Strategy Type Journal Article
Year 2015 Publication Neurocomputing Abbreviated Journal NEUCOM
Volume 150 Issue A Pages 106–115
Keywords (up) Reinforcement learning; Q-learning; Bag of features; Descriptors
Abstract This paper presents and evaluates a framework to improve the performance of visual object classification methods, which are based on the usage of image feature descriptors as inputs. The goal of the proposed framework is to learn the best descriptor for each image in a given database. This goal is reached by means of a reinforcement learning process using the minimum information. The visual classification system used to demonstrate the proposed framework is based on a bag of features scheme, and the reinforcement learning technique is implemented through the Q-learning approach. The behavior of the reinforcement learning with different state definitions is evaluated. Additionally, a method that combines all these states is formulated in order to select the optimal state. Finally, the chosen actions are obtained from the best set of image descriptors in the literature: PHOW, SIFT, C-SIFT, SURF and Spin. Experimental results using two public databases (ETH and COIL) are provided showing both the validity of the proposed approach and comparisons with state of the art. In all the cases the best results are obtained with the proposed approach.
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; 600.055; 600.076 Approved no
Call Number Admin @ si @ PST2015 Serial 2473
Permanent link to this record