Home | [191–200] << 201 202 203 204 205 206 207 208 209 210 >> [211–220] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Guillermo Torres; Sonia Baeza; Carles Sanchez; Ignasi Guasch; Antoni Rosell; Debora Gil | ||||
Title | An Intelligent Radiomic Approach for Lung Cancer Screening | Type | Journal Article | ||
Year | 2022 | Publication | Applied Sciences | Abbreviated Journal | APPLSCI |
Volume | 12 | Issue | 3 | Pages | 1568 |
Keywords | Lung cancer; Early diagnosis; Screening; Neural networks; Image embedding; Architecture optimization | ||||
Abstract | The efficiency of lung cancer screening for reducing mortality is hindered by the high rate of false positives. Artificial intelligence applied to radiomics could help to early discard benign cases from the analysis of CT scans. The available amount of data and the fact that benign cases are a minority, constitutes a main challenge for the successful use of state of the art methods (like deep learning), which can be biased, over-fitted and lack of clinical reproducibility. We present an hybrid approach combining the potential of radiomic features to characterize nodules in CT scans and the generalization of the feed forward networks. In order to obtain maximal reproducibility with minimal training data, we propose an embedding of nodules based on the statistical significance of radiomic features for malignancy detection. This representation space of lesions is the input to a feed
forward network, which architecture and hyperparameters are optimized using own-defined metrics of the diagnostic power of the whole system. Results of the best model on an independent set of patients achieve 100% of sensitivity and 83% of specificity (AUC = 0.94) for malignancy detection. |
||||
Address | Jan 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 | IAM; 600.139; 600.145 | Approved | no | ||
Call Number | Admin @ si @ TBS2022 | Serial | 3699 | ||
Permanent link to this record | |||||
Author | Bojana Gajic; Ariel Amato; Ramon Baldrich; Joost Van de Weijer; Carlo Gatta | ||||
Title | Area Under the ROC Curve Maximization for Metric Learning | Type | Conference Article | ||
Year | 2022 | Publication | CVPR 2022 Workshop on Efficien Deep Learning for Computer Vision (ECV 2022, 5th Edition) | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | Training; Computer vision; Conferences; Area measurement; Benchmark testing; Pattern recognition | ||||
Abstract | Most popular metric learning losses have no direct relation with the evaluation metrics that are subsequently applied to evaluate their performance. We hypothesize that training a metric learning model by maximizing the area under the ROC curve (which is a typical performance measure of recognition systems) can induce an implicit ranking suitable for retrieval problems. This hypothesis is supported by previous work that proved that a curve dominates in ROC space if and only if it dominates in Precision-Recall space. To test this hypothesis, we design and maximize an approximated, derivable relaxation of the area under the ROC curve. The proposed AUC loss achieves state-of-the-art results on two large scale retrieval benchmark datasets (Stanford Online Products and DeepFashion In-Shop). Moreover, the AUC loss achieves comparable performance to more complex, domain specific, state-of-the-art methods for vehicle re-identification. | ||||
Address | New Orleans, USA; 20 June 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 | CVPRW | ||
Notes | CIC; LAMP; | Approved | no | ||
Call Number | Admin @ si @ GAB2022 | Serial | 3700 | ||
Permanent link to this record | |||||
Author | Y. Mori; M.Misawa; Jorge Bernal; M. Bretthauer; S.Kudo; A. Rastogi; Gloria Fernandez Esparrach | ||||
Title | Artificial Intelligence for Disease Diagnosis-the Gold Standard Challenge | Type | Journal Article | ||
Year | 2022 | Publication | Gastrointestinal Endoscopy | Abbreviated Journal | |
Volume | 96 | Issue | 2 | Pages | 370-372 |
Keywords | |||||
Abstract | |||||
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 | Approved | no | ||
Call Number | Admin @ si @ MMB2022 | Serial | 3701 | ||
Permanent link to this record | |||||
Author | Juan Borrego-Carazo; Carles Sanchez; David Castells; Jordi Carrabina; Debora Gil | ||||
Title | BronchoPose: an analysis of data and model configuration for vision-based bronchoscopy pose estimation | Type | Journal Article | ||
Year | 2023 | Publication | Computer Methods and Programs in Biomedicine | Abbreviated Journal | CMPB |
Volume | 228 | Issue | Pages | 107241 | |
Keywords | Videobronchoscopy guiding; Deep learning; Architecture optimization; Datasets; Standardized evaluation framework; Pose estimation | ||||
Abstract | Vision-based bronchoscopy (VB) models require the registration of the virtual lung model with the frames from the video bronchoscopy to provide effective guidance during the biopsy. The registration can be achieved by either tracking the position and orientation of the bronchoscopy camera or by calibrating its deviation from the pose (position and orientation) simulated in the virtual lung model. Recent advances in neural networks and temporal image processing have provided new opportunities for guided bronchoscopy. However, such progress has been hindered by the lack of comparative experimental conditions.
In the present paper, we share a novel synthetic dataset allowing for a fair comparison of methods. Moreover, this paper investigates several neural network architectures for the learning of temporal information at different levels of subject personalization. In order to improve orientation measurement, we also present a standardized comparison framework and a novel metric for camera orientation learning. Results on the dataset show that the proposed metric and architectures, as well as the standardized conditions, provide notable improvements to current state-of-the-art camera pose estimation in video bronchoscopy. |
||||
Address | |||||
Corporate Author ![]() |
Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | IAM; | Approved | no | ||
Call Number | Admin @ si @ BSC2023 | Serial | 3702 | ||
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 | Alex Gomez-Villa; Bartlomiej Twardowski; Lu Yu; Andrew Bagdanov; Joost Van de Weijer | ||||
Title | Continually Learning Self-Supervised Representations With Projected Functional Regularization | Type | Conference Article | ||
Year | 2022 | Publication | CVPR 2022 Workshop on Continual Learning (CLVision, 3rd Edition) | Abbreviated Journal | |
Volume | Issue | Pages | 3866-3876 | ||
Keywords | Computer vision; Conferences; Self-supervised learning; Image representation; Pattern recognition | ||||
Abstract | Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally – they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay
mechanism. We show that naive functional regularization,also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional Regularization in which a separate temporal projection network ensures that the newly learned feature space preserves information of the previous one, while at the same time allowing for the learning of new features. This prevents forgetting while maintaining the plasticity of the learner. Comparison with other incremental learning approaches applied to self-supervision demonstrates that our method obtains competitive performance in different scenarios and on multiple datasets. |
||||
Address | New Orleans, USA; 20 June 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 | CVPRW | ||
Notes | LAMP: 600.147; 600.120 | Approved | no | ||
Call Number | Admin @ si @ GTY2022 | Serial | 3704 | ||
Permanent link to this record | |||||
Author | Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez | ||||
Title | Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models | Type | Journal Article | ||
Year | 2023 | Publication | Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction” | Abbreviated Journal | SENS |
Volume | 23 | Issue | 2 | Pages | 621 |
Keywords | Domain adaptation; semi-supervised learning; Semantic segmentation; Autonomous driving | ||||
Abstract | Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic
segmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overall procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Our procedure shows improvements ranging from ∼13 to ∼26 mIoU points over baselines, so establishing new state-of-the-art results. |
||||
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; no proj | Approved | no | ||
Call Number | Admin @ si @ GVL2023 | Serial | 3705 | ||
Permanent link to this record | |||||
Author | Reuben Dorent; Aaron Kujawa; Marina Ivory; Spyridon Bakas; Nikola Rieke; Samuel Joutard; Ben Glocker; Jorge Cardoso; Marc Modat; Kayhan Batmanghelich; Arseniy Belkov; Maria Baldeon Calisto; Jae Won Choi; Benoit M. Dawant; Hexin Dong; Sergio Escalera; Yubo Fan; Lasse Hansen; Mattias P. Heinrich; Smriti Joshi; Victoriya Kashtanova; Hyeon Gyu Kim; Satoshi Kondo; Christian N. Kruse; Susana K. Lai-Yuen; Hao Li; Han Liu; Buntheng Ly; Ipek Oguz; Hyungseob Shin; Boris Shirokikh; Zixian Su; Guotai Wang; Jianghao Wu; Yanwu Xu; Kai Yao; Li Zhang; Sebastien Ourselin, | ||||
Title | CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation | Type | Journal Article | ||
Year | 2023 | Publication | Medical Image Analysis | Abbreviated Journal | MIA |
Volume | 83 | Issue | Pages | 102628 | |
Keywords | Domain Adaptation; Segmen tation; Vestibular Schwnannoma | ||||
Abstract | Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques has been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA. The challenge's goal is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are performed using contrast-enhanced T1 (ceT1) MRI. However, there is growing interest in using non-contrast sequences such as high-resolution T2 (hrT2) MRI. Therefore, we created an unsupervised cross-modality segmentation benchmark. The training set provides annotated ceT1 (N=105) and unpaired non-annotated hrT2 (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137). A total of 16 teams submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice – VS:88.4%; Cochleas:85.7%) and close to full supervision (median Dice – VS:92.5%; Cochleas:87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image. | ||||
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 | Approved | no | ||
Call Number | Admin @ si @ DKI2023 | Serial | 3706 | ||
Permanent link to this record | |||||
Author | Julio C. S. Jacques Junior; Yagmur Gucluturk; Marc Perez; Umut Guçlu; Carlos Andujar; Xavier Baro; Hugo Jair Escalante; Isabelle Guyon; Marcel A. J. van Gerven; Rob van Lier; Sergio Escalera | ||||
Title | First Impressions: A Survey on Vision-Based Apparent Personality Trait Analysis | Type | Journal Article | ||
Year | 2022 | Publication | IEEE Transactions on Affective Computing | Abbreviated Journal | TAC |
Volume | 13 | Issue | 1 | Pages | 75-95 |
Keywords | Personality computing; first impressions; person perception; big-five; subjective bias; computer vision; machine learning; nonverbal signals; facial expression; gesture; speech analysis; multi-modal recognition | ||||
Abstract | Personality analysis has been widely studied in psychology, neuropsychology, and signal processing fields, among others. From the past few years, it also became an attractive research area in visual computing. From the computational point of view, by far speech and text have been the most considered cues of information for analyzing personality. However, recently there has been an increasing interest from the computer vision community in analyzing personality from visual data. Recent computer vision approaches are able to accurately analyze human faces, body postures and behaviors, and use these information to infer apparent personality traits. Because of the overwhelming research interest in this topic, and of the potential impact that this sort of methods could have in society, we present in this paper an up-to-date review of existing vision-based approaches for apparent personality trait recognition. We describe seminal and cutting edge works on the subject, discussing and comparing their distinctive features and limitations. Future venues of research in the field are identified and discussed. Furthermore, aspects on the subjectivity in data labeling/evaluation, as well as current datasets and challenges organized to push the research on the field are reviewed. | ||||
Address | 1 Jan.-March 2022 | ||||
Corporate Author ![]() |
Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | HuPBA | Approved | no | ||
Call Number | Admin @ si @ JGP2022 | Serial | 3724 | ||
Permanent link to this record | |||||
Author | Gemma Rotger; Francesc Moreno-Noguer; Felipe Lumbreras; Antonio Agudo | ||||
Title | Single view facial hair 3D reconstruction | Type | Conference Article | ||
Year | 2019 | Publication | 9th Iberian Conference on Pattern Recognition and Image Analysis | Abbreviated Journal | |
Volume | 11867 | Issue | Pages | 423-436 | |
Keywords | 3D Vision; Shape Reconstruction; Facial Hair Modeling | ||||
Abstract | n this work, we introduce a novel energy-based framework that addresses the challenging problem of 3D reconstruction of facial hair from a single RGB image. To this end, we identify hair pixels over the image via texture analysis and then determine individual hair fibers that are modeled by means of a parametric hair model based on 3D helixes. We propose to minimize an energy composed of several terms, in order to adapt the hair parameters that better fit the image detections. The final hairs respond to the resulting fibers after a post-processing step where we encourage further realism. The resulting approach generates realistic facial hair fibers from solely an RGB image without assuming any training data nor user interaction. We provide an experimental evaluation on real-world pictures where several facial hair styles and image conditions are observed, showing consistent results and establishing a comparison with respect to competing approaches. | ||||
Address | Madrid; July 2019 | ||||
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 | IbPRIA | ||
Notes | MSIAU; 600.086; 600.130; 600.122 | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3707 | ||
Permanent link to this record | |||||
Author | Gemma Rotger; Francesc Moreno-Noguer; Felipe Lumbreras; Antonio Agudo | ||||
Title | Detailed 3D face reconstruction from a single RGB image | Type | Journal | ||
Year | 2019 | Publication | Journal of WSCG | Abbreviated Journal | JWSCG |
Volume | 27 | Issue | 2 | Pages | 103-112 |
Keywords | 3D Wrinkle Reconstruction; Face Analysis, Optimization. | ||||
Abstract | This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image.
To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles. |
||||
Address | 2019/11 | ||||
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 | MSIAU; 600.086; 600.130; 600.122 | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3708 | ||
Permanent link to this record | |||||
Author | Bojana Gajic; Ramon Baldrich | ||||
Title | Cross-domain fashion image retrieval | Type | Conference Article | ||
Year | 2018 | Publication | CVPR 2018 Workshop on Women in Computer Vision (WiCV 2018, 4th Edition) | Abbreviated Journal | |
Volume | Issue | Pages | 19500-19502 | ||
Keywords | |||||
Abstract | Cross domain image retrieval is a challenging task that implies matching images from one domain to their pairs from another domain. In this paper we focus on fashion image retrieval, which involves matching an image of a fashion item taken by users, to the images of the same item taken in controlled condition, usually by professional photographer. When facing this problem, we have different products
in train and test time, and we use triplet loss to train the network. We stress the importance of proper training of simple architecture, as well as adapting general models to the specific task. |
||||
Address | Salt Lake City, USA; 22 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 | CVPRW | ||
Notes | CIC; 600.087 | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3709 | ||
Permanent link to this record | |||||
Author | Bojana Gajic; Eduard Vazquez; Ramon Baldrich | ||||
Title | Evaluation of Deep Image Descriptors for Texture Retrieval | Type | Conference Article | ||
Year | 2017 | Publication | Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) | Abbreviated Journal | |
Volume | Issue | Pages | 251-257 | ||
Keywords | Texture Representation; Texture Retrieval; Convolutional Neural Networks; Psychophysical Evaluation | ||||
Abstract | The increasing complexity learnt in the layers of a Convolutional Neural Network has proven to be of great help for the task of classification. The topic has received great attention in recently published literature.
Nonetheless, just a handful of works study low-level representations, commonly associated with lower layers. In this paper, we explore recent findings which conclude, counterintuitively, the last layer of the VGG convolutional network is the best to describe a low-level property such as texture. To shed some light on this issue, we are proposing a psychophysical experiment to evaluate the adequacy of different layers of the VGG network for texture retrieval. Results obtained suggest that, whereas the last convolutional layer is a good choice for a specific task of classification, it might not be the best choice as a texture descriptor, showing a very poor performance on texture retrieval. Intermediate layers show the best performance, showing a good combination of basic filters, as in the primary visual cortex, and also a degree of higher level information to describe more complex textures. |
||||
Address | Porto, Portugal; 27 February – 1 March 2017 | ||||
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 | CIC; 600.087 | Approved | no | ||
Call Number | Admin @ si @ | Serial | 3710 | ||
Permanent link to this record | |||||
Author | Jon Almazan; Bojana Gajic; Naila Murray; Diane Larlus | ||||
Title | Re-ID done right: towards good practices for person re-identification | Type | Miscellaneous | ||
Year | 2018 | Publication | Arxiv | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism. | ||||
Address | January 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 | |||
Notes | Approved | no | |||
Call Number | Admin @ si @ | Serial | 3711 | ||
Permanent link to this record | |||||
Author | Akhil Gurram | ||||
Title | Monocular Depth Estimation for Autonomous Driving | Type | Book Whole | ||
Year | 2022 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | 3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV.
Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol. After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>. Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect. |
||||
Address | March, 2022 | ||||
Corporate Author ![]() |
Thesis | Ph.D. thesis | |||
Publisher | IMPRIMA | Place of Publication | Editor | Antonio Lopez;Onay Urfalioglu | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-124793-0-0 | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS | Approved | no | ||
Call Number | Admin @ si @ Gur2022 | Serial | 3712 | ||
Permanent link to this record |