Home | [61–70] << 71 72 73 74 75 76 77 78 79 80 >> [81–90] |
Records | |||||
---|---|---|---|---|---|
Author | Jürgen Brauer; Wenjuan Gong; Jordi Gonzalez; Michael Arens | ||||
Title | On the Effect of Temporal Information on Monocular 3D Human Pose Estimation | Type | Conference Article | ||
Year | 2011 | Publication | 2nd IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams | Abbreviated Journal | |
Volume | Issue | Pages | 906 - 913 | ||
Keywords | |||||
Abstract | We address the task of estimating 3D human poses from monocular camera sequences. Many works make use of multiple consecutive frames for the estimation of a 3D pose in a frame. Although such an approach should ease the pose estimation task substantially since multiple consecutive frames allow to solve for 2D projection ambiguities in principle, it has not yet been investigated systematically how much we can improve the 3D pose estimates when using multiple consecutive frames opposed to single frame information. In this paper we analyze the difference in quality of 3D pose estimates based on different numbers of consecutive frames from which 2D pose estimates are available. We validate the use of temporal information on two major different approaches for human pose estimation – modeling and learning approaches. The results of our experiments show that both learning and modeling approaches benefit from using multiple frames opposed to single frame input but that the benefit is small when the 2D pose estimates show a high quality in terms of precision. | ||||
Address | Barcelona | ||||
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 | 978-1-4673-0062-9 | Medium | ||
Area | Expedition | Conference | ARTEMIS | ||
Notes | ISE | Approved | no | ||
Call Number | Admin @ si @BGG 2011 | Serial | 1860 | ||
Permanent link to this record | |||||
Author | Simone Balocco; Carlo Gatta; Marina Alberti; Xavier Carrillo; Juan Rigla; Petia Radeva | ||||
Title | Relation between plaque type, plaque thickness, blood shear stress and plaque stress in coronary arteries assessed by X-ray Angiography and Intravascular Ultrasound | Type | Journal Article | ||
Year | 2012 | Publication | Medical Physics | Abbreviated Journal | MEDPHYS |
Volume | 39 | Issue | 12 | Pages | 7430-7445 |
Keywords | |||||
Abstract | PMID 23231293
PURPOSE: Atheromatic plaque progression is affected, among others phenomena, by biomechanical, biochemical, and physiological factors. In this paper, the authors introduce a novel framework able to provide both morphological (vessel radius, plaque thickness, and type) and biomechanical (wall shear stress and Von Mises stress) indices of coronary arteries. METHODS: First, the approach reconstructs the three-dimensional morphology of the vessel from intravascular ultrasound (IVUS) and Angiographic sequences, requiring minimal user interaction. Then, a computational pipeline allows to automatically assess fluid-dynamic and mechanical indices. Ten coronary arteries are analyzed illustrating the capabilities of the tool and confirming previous technical and clinical observations. RESULTS: The relations between the arterial indices obtained by IVUS measurement and simulations have been quantitatively analyzed along the whole surface of the artery, extending the analysis of the coronary arteries shown in previous state of the art studies. Additionally, for the first time in the literature, the framework allows the computation of the membrane stresses using a simplified mechanical model of the arterial wall. CONCLUSIONS: Circumferentially (within a given frame), statistical analysis shows an inverse relation between the wall shear stress and the plaque thickness. At the global level (comparing a frame within the entire vessel), it is observed that heavy plaque accumulations are in general calcified and are located in the areas of the vessel having high wall shear stress. Finally, in their experiments the inverse proportionality between fluid and structural stresses is observed. |
||||
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 @BGA2012 | Serial | 2170 | ||
Permanent link to this record | |||||
Author | Cristhian A. Aguilera-Carrasco | ||||
Title | Evaluation of feature detectors and descriptors in VISIBLE-LWIR cross-spectral imaging | Type | Report | ||
Year | 2014 | Publication | CVC Technical Report | Abbreviated Journal | |
Volume | 177 | Issue | Pages | ||
Keywords | Multi-spectral; Cross-spectral; Visible-LWIR imaging; Multimodal. | ||||
Abstract | This thesis evaluates the performance of different state-of-art feature detectors and descriptors algorithms in the Visible-LWIR cross-spectral scenario. The focus is to determine if current detector and descriptor algorithms can be used to match features between the LWIR spectrum and the visible spectrum in applications such as, visual odometry, object recognition, image registration and stereo vision. An outdoor cross-spectral dataset was created to evaluate the suitability of the different algorithms. The results
show that the tested algorithms are not suitable to the task of matching features across different spectra. The repeatability ratio was smaller than the 30 percent in the best case and in general matched features were not accurate located. Additionally, these results also suggest that is necessary to create new algorithms that take into account the nature of the different spectra, describing characteristics that exist in both spectra such as discontinuities. |
||||
Address | |||||
Corporate Author | Thesis | Master's 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; 600.076 | Approved | no | ||
Call Number | Admin @ si @Agu2014 | Serial | 2526 | ||
Permanent link to this record | |||||
Author | Maedeh Aghaei; Mariella Dimiccoli; Petia Radeva | ||||
Title | With whom do I interact with? Social interaction detection in egocentric photo-streams | Type | Conference Article | ||
Year | 2016 | Publication | 23rd International Conference on Pattern Recognition | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Given a user wearing a low frame rate wearable camera during a day, this work aims to automatically detect the moments when the user gets engaged into a social interaction solely by reviewing the automatically captured photos by the worn camera. The proposed method, inspired by the sociological concept of F-formation, exploits distance and orientation of the appearing individuals -with respect to the user- in the scene from a bird-view perspective. As a result, the interaction pattern over the sequence can be understood as a two-dimensional time series that corresponds to the temporal evolution of the distance and orientation features over time. A Long-Short Term Memory-based Recurrent Neural Network is then trained to classify each time series. Experimental evaluation over a dataset of 30.000 images has shown promising results on the proposed method for social interaction detection in egocentric photo-streams. | ||||
Address | Cancun; Mexico; December 2016 | ||||
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 | ICPR | ||
Notes | MILAB | Approved | no | ||
Call Number | Admin @ si @ADR2016a | Serial | 2791 | ||
Permanent link to this record | |||||
Author | Cristhian A. Aguilera-Carrasco; F. Aguilera; Angel Sappa; C. Aguilera; Ricardo Toledo | ||||
Title | Learning cross-spectral similarity measures with deep convolutional neural networks | Type | Conference Article | ||
Year | 2016 | Publication | 29th IEEE Conference on Computer Vision and Pattern Recognition Worshops | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | The simultaneous use of images from different spectracan be helpful to improve the performance of many computer vision tasks. The core idea behind the usage of crossspectral approaches is to take advantage of the strengths of each spectral band providing a richer representation of a scene, which cannot be obtained with just images from one spectral band. In this work we tackle the cross-spectral image similarity problem by using Convolutional Neural Networks (CNNs). We explore three different CNN architectures to compare the similarity of cross-spectral image patches. Specifically, we train each network with images from the visible and the near-infrared spectrum, and then test the result with two public cross-spectral datasets. Experimental results show that CNN approaches outperform the current state-of-art on both cross-spectral datasets. Additionally, our experiments show that some CNN architectures are capable of generalizing between different crossspectral domains. | ||||
Address | Las vegas; USA; June 2016 | ||||
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 | CVPRW | ||
Notes | ADAS; 600.086; 600.076 | Approved | no | ||
Call Number | Admin @ si @AAS2016 | Serial | 2809 | ||
Permanent link to this record | |||||
Author | Jose M. Armingol; Jorge Alfonso; Nourdine Aliane; Miguel Clavijo; Sergio Campos-Cordobes; Arturo de la Escalera; Javier del Ser; Javier Fernandez; Fernando Garcia; Felipe Jimenez; Antonio Lopez; Mario Mata | ||||
Title | Environmental Perception for Intelligent Vehicles | Type | Book Chapter | ||
Year | 2018 | Publication | Intelligent Vehicles. Enabling Technologies and Future Developments | Abbreviated Journal | |
Volume | Issue | Pages | 23–101 | ||
Keywords | Computer vision; laser techniques; data fusion; advanced driver assistance systems; traffic monitoring systems; intelligent vehicles | ||||
Abstract | Environmental perception represents, because of its complexity, a challenge for Intelligent Transport Systems due to the great variety of situations and different elements that can happen in road environments and that must be faced by these systems. In connection with this, so far there are a variety of solutions as regards sensors and methods, so the results of precision, complexity, cost, or computational load obtained by these works are different. In this chapter some systems based on computer vision and laser techniques are presented. Fusion methods are also introduced in order to provide advanced and reliable perception systems. | ||||
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; 600.118 | Approved | no | ||
Call Number | Admin @ si @AAA2018 | Serial | 3046 | ||
Permanent link to this record | |||||
Author | Chengyi Zou; Shuai Wan; Marta Mrak; Marc Gorriz Blanch; Luis Herranz; Tiannan Ji | ||||
Title | Towards Lightweight Neural Network-based Chroma Intra Prediction for Video Coding | Type | Conference Article | ||
Year | 2022 | Publication | 29th IEEE International Conference on Image Processing | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | Video coding; Quantization (signal); Computational modeling; Neural networks; Predictive models; Video compression; Syntactics | ||||
Abstract | In video compression the luma channel can be useful for predicting chroma channels (Cb, Cr), as has been demonstrated with the Cross-Component Linear Model (CCLM) used in Versatile Video Coding (VVC) standard. More recently, it has been shown that neural networks can even better capture the relationship among different channels. In this paper, a new attention-based neural network is proposed for cross-component intra prediction. With the goal to simplify neural network design, the new framework consists of four branches: boundary branch and luma branch for extracting features from reference samples, attention branch for fusing the first two branches, and prediction branch for computing the predicted chroma samples. The proposed scheme is integrated into VVC test model together with one additional binary block-level syntax flag which indicates whether a given block makes use of the proposed method. Experimental results demonstrate 0.31%/2.36%/2.00% BD-rate reductions on Y/Cb/Cr components, respectively, on top of the VVC Test Model (VTM) 7.0 which uses CCLM. | ||||
Address | Bordeaux; France; October 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 | ICIP | ||
Notes | MACO | Approved | no | ||
Call Number | Admin @ si @ ZWM2022 | Serial | 3790 | ||
Permanent link to this record | |||||
Author | Javad Zolfaghari Bengar; Joost Van de Weijer; Laura Lopez-Fuentes; Bogdan Raducanu | ||||
Title | Class-Balanced Active Learning for Image Classification | Type | Conference Article | ||
Year | 2022 | Publication | Winter Conference on Applications of Computer Vision | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called long-tail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we proposed a general optimization framework that explicitly takes class-balancing into account. Results on three datasets showed that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we showed that also on balanced datasets
our method 1 generally results in a performance gain. |
||||
Address | Virtual; Waikoloa; Hawai; USA; January 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 | WACV | ||
Notes | LAMP; 602.200; 600.147; 600.120 | Approved | no | ||
Call Number | Admin @ si @ ZWL2022 | Serial | 3703 | ||
Permanent link to this record | |||||
Author | Shifeng Zhang; Xiaobo Wang; Ajian Liu; Chenxu Zhao; Jun Wan; Sergio Escalera; Hailin Shi; Zezheng Wang; Stan Z. Li | ||||
Title | A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing | Type | Conference Article | ||
Year | 2019 | Publication | 32nd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
Volume | Issue | Pages | 919-928 | ||
Keywords | |||||
Abstract | Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects (≤170) and modalities (≤2), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities. Specifically, it consists of 1,000 subjects with 21,000 videos and each sample has 3 modalities (i.e., RGB, Depth and IR). We also provide a measurement set, evaluation protocol and training/validation/testing subsets, developing a new benchmark for face anti-spoofing. Moreover, we present a new multi-modal fusion method as baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modal. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/chalearnfacespoofingattackdete/. | ||||
Address | California; 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 | CVPR | ||
Notes | HuPBA; no proj | Approved | no | ||
Call Number | Admin @ si @ ZWL2019 | Serial | 3331 | ||
Permanent link to this record | |||||
Author | Chengyi Zou; Shuai Wan; Tiannan Ji; Marc Gorriz Blanch; Marta Mrak; Luis Herranz | ||||
Title | Chroma Intra Prediction with Lightweight Attention-Based Neural Networks | Type | Journal Article | ||
Year | 2023 | Publication | IEEE Transactions on Circuits and Systems for Video Technology | Abbreviated Journal | TCSVT |
Volume | 34 | Issue | 1 | Pages | 549 - 560 |
Keywords | |||||
Abstract | Neural networks can be successfully used for cross-component prediction in video coding. In particular, attention-based architectures are suitable for chroma intra prediction using luma information because of their capability to model relations between difierent channels. However, the complexity of such methods is still very high and should be further reduced, especially for decoding. In this paper, a cost-effective attention-based neural network is designed for chroma intra prediction. Moreover, with the goal of further improving coding performance, a novel approach is introduced to utilize more boundary information effectively. In addition to improving prediction, a simplification methodology is also proposed to reduce inference complexity by simplifying convolutions. The proposed schemes are integrated into H.266/Versatile Video Coding (VVC) pipeline, and only one additional binary block-level syntax flag is introduced to indicate whether a given block makes use of the proposed method. Experimental results demonstrate that the proposed scheme achieves up to −0.46%/−2.29%/−2.17% BD-rate reduction on Y/Cb/Cr components, respectively, compared with H.266/VVC anchor. Reductions in the encoding and decoding complexity of up to 22% and 61%, respectively, are achieved by the proposed scheme with respect to the previous attention-based chroma intra prediction method while maintaining coding 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 | MACO; LAMP | Approved | no | ||
Call Number | Admin @ si @ ZWJ2023 | Serial | 3875 | ||
Permanent link to this record | |||||
Author | Javad Zolfaghari Bengar; Joost Van de Weijer; Bartlomiej Twardowski; Bogdan Raducanu | ||||
Title | Reducing Label Effort: Self- Supervised Meets Active Learning | Type | Conference Article | ||
Year | 2021 | Publication | International Conference on Computer Vision Workshops | Abbreviated Journal | |
Volume | Issue | Pages | 1631-1639 | ||
Keywords | |||||
Abstract | Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent developments in self-training have achieved very impressive results rivaling supervised learning on some datasets. The current work focuses on whether the two paradigms can benefit from each other. We studied object recognition datasets including CIFAR10, CIFAR100 and Tiny ImageNet with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high. The performance gap between active learning trained either with self-training or from scratch diminishes as we approach to the point where almost half of the dataset is labeled. | ||||
Address | October 2021 | ||||
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 @ ZVT2021 | Serial | 3672 | ||
Permanent link to this record | |||||
Author | Chen Zhang; Maria del Mar Vila Muñoz; Petia Radeva; Roberto Elosua; Maria Grau; Angels Betriu; Elvira Fernandez-Giraldez; Laura Igual | ||||
Title | Carotid Artery Segmentation in Ultrasound Images | Type | Conference Article | ||
Year | 2015 | Publication | Computing and Visualization for Intravascular Imaging and Computer Assisted Stenting (CVII-STENT2015), Joint MICCAI Workshops | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | Munich; Germany; October 2015 | ||||
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 | CVII-STENT | ||
Notes | MILAB | Approved | no | ||
Call Number | Admin @ si @ ZVR2015 | Serial | 2675 | ||
Permanent link to this record | |||||
Author | Ekaterina Zaytseva; Santiago Segui; Jordi Vitria | ||||
Title | Sketchable Histograms of Oriented Gradients for Object Detection | Type | Conference Article | ||
Year | 2012 | Publication | 17th Iberomerican Conference on Pattern Recognition | Abbreviated Journal | |
Volume | 7441 | Issue | Pages | 374-381 | |
Keywords | |||||
Abstract | In this paper we investigate a new representation approach for visual object recognition. The new representation, called sketchable-HoG, extends the classical histogram of oriented gradients (HoG) feature by adding two different aspects: the stability of the majority orientation and the continuity of gradient orientations. In this way, the sketchable-HoG locally characterizes the complexity of an object model and introduces global structure information while still keeping simplicity, compactness and robustness. We evaluated the proposed image descriptor on publicly Catltech 101 dataset. The obtained results outperforms classical HoG descriptor as well as other reported descriptors in the literature. | ||||
Address | Buenos Aires, Argentina | ||||
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 | 978-3-642-33274-6 | Medium | |
Area | Expedition | Conference | CIARP | ||
Notes | OR; MILAB;MV | Approved | no | ||
Call Number | Admin @ si @ ZSV2012 | Serial | 2048 | ||
Permanent link to this record | |||||
Author | Javad Zolfaghari Bengar; Bogdan Raducanu; Joost Van de Weijer | ||||
Title | When Deep Learners Change Their Mind: Learning Dynamics for Active Learning | Type | Conference Article | ||
Year | 2021 | Publication | 19th International Conference on Computer Analysis of Images and Patterns | Abbreviated Journal | |
Volume | 13052 | Issue | 1 | Pages | 403-413 |
Keywords | |||||
Abstract | Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results. | ||||
Address | September 2021 | ||||
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 | CAIP | ||
Notes | LAMP; | Approved | no | ||
Call Number | Admin @ si @ ZRV2021 | Serial | 3673 | ||
Permanent link to this record | |||||
Author | Javad Zolfaghari Bengar | ||||
Title | Reducing Label Effort with Deep Active Learning | Type | Book Whole | ||
Year | 2021 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition applications, such as image classification, detection and segmentation. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected
informative and/or representative samples. In this thesis we study several aspects of active learning including video object detection for autonomous driving systems, image classification on balanced and imbalanced datasets and the incorporation of self-supervised learning in active learning. We briefly describe our approach in each of these areas to reduce the labeling effort. In chapter two we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our criterion is based on the estimated number of errors in terms of false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active learning for video object detection in road scenes. Finally, we show that our approach outperforms active learning baselines tested on two outdoor datasets. In the next chapter we address the well-known problem of over confidence in the neural networks. As an alternative to network confidence, we propose a new informativeness-based active learning method that captures the learning dynamics of neural network with a metric called label-dispersion. This metric is low when the network consistently assigns the same label to the sample during the course of training and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results. In chapter four, we tackle the problem of sampling bias in active learning methods on imbalanced datasets. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called longtail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we propose a general optimization framework that explicitly takes class-balancing into account. Results on three datasets show that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we show that also on balanced datasets our method generally results in a performance gain. Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent advancements in self-training have achieved very impressive results rivaling supervised learning on some datasets. In the last chapter we focus on whether active learning and self supervised learning can benefit from each other. We study object recognition datasets with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high. |
||||
Address | December 2021 | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | IMPRIMA | Place of Publication | Editor | Joost Van de Weijer;Bogdan Raducanu | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-122714-9-2 | Medium | ||
Area | Expedition | Conference | |||
Notes | LAMP; | Approved | no | ||
Call Number | Admin @ si @ Zol2021 | Serial | 3609 | ||
Permanent link to this record |