|
Records |
Links |
|
Author |
Victoria Ruiz; Angel Sanchez; Jose F. Velez; Bogdan Raducanu |
![goto web page (via DOI) doi](img/doi.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Waste Classification with Small Datasets and Limited Resources |
Type |
Book Chapter |
|
Year |
2022 |
Publication |
ICT Applications for Smart Cities. Intelligent Systems Reference Library |
Abbreviated Journal |
|
|
|
Volume |
224 |
Issue |
|
Pages |
185-203 |
|
|
Keywords |
|
|
|
Abstract |
Automatic waste recycling has become a very important societal challenge nowadays, raising people’s awareness for a cleaner environment and a more sustainable lifestyle. With the transition to Smart Cities, and thanks to advanced ICT solutions, this problem has received a new impulse. The waste recycling focus has shifted from general waste treating facilities to an individual responsibility, where each person should become aware of selective waste separation. The surge of the mobile devices, accompanied by a significant increase in computation power, has potentiated and facilitated this individual role. An automated image-based waste classification mechanism can help with a more efficient recycling and a reduction of contamination from residuals. Despite the good results achieved with the deep learning methodologies for this task, the Achille’s heel is that they require large neural networks which need significant computational resources for training and therefore are not suitable for mobile devices. To circumvent this apparently intractable problem, we will rely on knowledge distillation in order to transfer the network’s knowledge from a larger network (called ‘teacher’) to a smaller, more compact one, (referred as ‘student’) and thus making it possible the task of image classification on a device with limited resources. For evaluation, we considered as ‘teachers’ large architectures such as InceptionResNet or DenseNet and as ‘students’, several configurations of the MobileNets. We used the publicly available TrashNet dataset to demonstrate that the distillation process does not significantly affect system’s performance (e.g. classification accuracy) of the student network. |
|
|
Address |
September 2022 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
Springer |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
ISRL |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
978-3-031-06306-0 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
Admin @ si @ |
Serial |
3813 |
|
Permanent link to this record |
|
|
|
|
Author |
Akshita Gupta; Sanath Narayan; Salman Khan; Fahad Shahbaz Khan; Ling Shao; Joost Van de Weijer |
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Generative Multi-Label Zero-Shot Learning |
Type |
Journal Article |
|
Year |
2023 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
|
Volume |
45 |
Issue |
12 |
Pages |
14611-14624 |
|
|
Keywords |
Generalized zero-shot learning; Multi-label classification; Zero-shot object detection; Feature synthesis |
|
|
Abstract |
Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods. |
|
|
Address |
December 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP; PID2021-128178OB-I00 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
Admin @ si @ |
Serial |
3853 |
|
Permanent link to this record |
|
|
|
|
Author |
Jose Elias Yauri; M. Lagos; H. Vega-Huerta; P. de-la-Cruz; G.L.E Maquen-Niño; E. Condor-Tinoco |
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Detection of Epileptic Seizures Based-on Channel Fusion and Transformer Network in EEG Recordings |
Type |
Journal Article |
|
Year |
2023 |
Publication |
International Journal of Advanced Computer Science and Applications |
Abbreviated Journal |
IJACSA |
|
|
Volume |
14 |
Issue |
5 |
Pages |
1067-1074 |
|
|
Keywords |
Epilepsy; epilepsy detection; EEG; EEG channel fusion; convolutional neural network; self-attention |
|
|
Abstract |
According to the World Health Organization, epilepsy affects more than 50 million people in the world, and specifically, 80% of them live in developing countries. Therefore, epilepsy has become among the major public issue for many governments and deserves to be engaged. Epilepsy is characterized by uncontrollable seizures in the subject due to a sudden abnormal functionality of the brain. Recurrence of epilepsy attacks change people’s lives and interferes with their daily activities. Although epilepsy has no cure, it could be mitigated with an appropriated diagnosis and medication. Usually, epilepsy diagnosis is based on the analysis of an electroencephalogram (EEG) of the patient. However, the process of searching for seizure patterns in a multichannel EEG recording is a visual demanding and time consuming task, even for experienced neurologists. Despite the recent progress in automatic recognition of epilepsy, the multichannel nature of EEG recordings still challenges current methods. In this work, a new method to detect epilepsy in multichannel EEG recordings is proposed. First, the method uses convolutions to perform channel fusion, and next, a self-attention network extracts temporal features to classify between interictal and ictal epilepsy states. The method was validated in the public CHB-MIT dataset using the k-fold cross-validation and achieved 99.74% of specificity and 99.15% of sensitivity, surpassing current approaches. |
|
|
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 |
IAM |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
Admin @ si @ |
Serial |
3856 |
|
Permanent link to this record |
|
|
|
|
Author |
M. Altillawi; S. Li; S.M. Prakhya; Z. Liu; Joan Serrat |
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Implicit Learning of Scene Geometry From Poses for Global Localization |
Type |
Journal Article |
|
Year |
2024 |
Publication |
IEEE Robotics and Automation Letters |
Abbreviated Journal |
ROBOTAUTOMLET |
|
|
Volume |
9 |
Issue |
2 |
Pages |
955-962 |
|
|
Keywords |
Localization; Localization and mapping; Deep learning for visual perception; Visual learning |
|
|
Abstract |
Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics and augmented/virtual reality applications. Inspired by latest advances in deep learning, many existing approaches directly learn and regress 6 DoF pose from an input image. However, these methods do not fully utilize the underlying scene geometry for pose regression. The challenge in monocular relocalization is the minimal availability of supervised training data, which is just the corresponding 6 DoF poses of the images. In this letter, we propose to utilize these minimal available labels (i.e., poses) to learn the underlying 3D geometry of the scene and use the geometry to estimate the 6 DoF camera pose. We present a learning method that uses these pose labels and rigid alignment to learn two 3D geometric representations ( X, Y, Z coordinates ) of the scene, one in camera coordinate frame and the other in global coordinate frame. Given a single image, it estimates these two 3D scene representations, which are then aligned to estimate a pose that matches the pose label. This formulation allows for the active inclusion of additional learning constraints to minimize 3D alignment errors between the two 3D scene representations, and 2D re-projection errors between the 3D global scene representation and 2D image pixels, resulting in improved localization accuracy. During inference, our model estimates the 3D scene geometry in camera and global frames and aligns them rigidly to obtain pose in real-time. We evaluate our work on three common visual localization datasets, conduct ablation studies, and show that our method exceeds state-of-the-art regression methods' pose accuracy on all datasets. |
|
|
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 |
2377-3766 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
ADAS |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
Admin @ si @ |
Serial |
3857 |
|
Permanent link to this record |
|
|
|
|
Author |
Filip Szatkowski; Mateusz Pyla; Marcin Przewięzlikowski; Sebastian Cygert; Bartłomiej Twardowski; Tomasz Trzcinski |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning |
Type |
Conference Article |
|
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
3512-3517 |
|
|
Keywords |
|
|
|
Abstract |
In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher network when dealing with out-of-distribution data. This causes large errors in the KD loss component, leading to performance degradation in CIL. Inspired by recent test-time adaptation methods, we introduce Teacher Adaptation (TA), a method that concurrently updates the teacher and the main model during incremental training. Our method seamlessly integrates with KD-based CIL approaches and allows for consistent enhancement of their performance across multiple exemplar-free CIL benchmarks. |
|
|
Address |
Paris; France; October 2023 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICCVW |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
Admin @ si @ |
Serial |
3944 |
|
Permanent link to this record |
|
|
|
|
Author |
M.J. Yzuel; J. Pladellorens; Joan Serrat; A. Dupuy |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Application restauration and edge detection techniques in the calculation of left ventricular volumes. |
Type |
Conference Article |
|
Year |
1993 |
Publication |
Optics in Medicine, Biology and Environmental Research : Selected contributions to the first International Conference on Optics within Life Sciences (OWLS I) |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
374-375 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
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 |
ADAS |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ YPS1993 |
Serial |
244 |
|
Permanent link to this record |
|
|
|
|
Author |
Jiaolong Xu; David Vazquez; Antonio Lopez; Javier Marin; Daniel Ponsa |
![download PDF file pdf](img/file_PDF.gif)
![find book details (via ISBN) isbn](img/isbn.gif)
|
|
Title |
Learning a Part-based Pedestrian Detector in Virtual World |
Type |
Journal Article |
|
Year |
2014 |
Publication |
IEEE Transactions on Intelligent Transportation Systems |
Abbreviated Journal |
TITS |
|
|
Volume |
15 |
Issue |
5 |
Pages |
2121-2131 |
|
|
Keywords |
Domain Adaptation; Pedestrian Detection; Virtual Worlds |
|
|
Abstract |
Detecting pedestrians with on-board vision systems is of paramount interest for assisting drivers to prevent vehicle-to-pedestrian accidents. The core of a pedestrian detector is its classification module, which aims at deciding if a given image window contains a pedestrian. Given the difficulty of this task, many classifiers have been proposed during the last fifteen years. Among them, the so-called (deformable) part-based classifiers including multi-view modeling are usually top ranked in accuracy. Training such classifiers is not trivial since a proper aspect clustering and spatial part alignment of the pedestrian training samples are crucial for obtaining an accurate classifier. In this paper, first we perform automatic aspect clustering and part alignment by using virtual-world pedestrians, i.e., human annotations are not required. Second, we use a mixture-of-parts approach that allows part sharing among different aspects. Third, these proposals are integrated in a learning framework which also allows to incorporate real-world training data to perform domain adaptation between virtual- and real-world cameras. Overall, the obtained results on four popular on-board datasets show that our proposal clearly outperforms the state-of-the-art deformable part-based detector known as latent SVM. |
|
|
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 |
1931-0587 |
ISBN |
978-1-4673-2754-1 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
ADAS; 600.076 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ XVL2014 |
Serial |
2433 |
|
Permanent link to this record |
|
|
|
|
Author |
Jiaolong Xu; Sebastian Ramos; David Vazquez; Antonio Lopez |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Domain Adaptation of Deformable Part-Based Models |
Type |
Journal Article |
|
Year |
2014 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
|
Volume |
36 |
Issue |
12 |
Pages |
2367-2380 |
|
|
Keywords |
Domain Adaptation; Pedestrian Detection |
|
|
Abstract |
The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors. |
|
|
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 |
0162-8828 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
ADAS; 600.057; 600.054; 601.217; 600.076 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ XRV2014b |
Serial |
2436 |
|
Permanent link to this record |
|
|
|
|
Author |
Jiaolong Xu; Sebastian Ramos;David Vazquez; Antonio Lopez |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Cost-sensitive Structured SVM for Multi-category Domain Adaptation |
Type |
Conference Article |
|
Year |
2014 |
Publication |
22nd International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
3886 - 3891 |
|
|
Keywords |
Domain Adaptation; Pedestrian Detection |
|
|
Abstract |
Domain adaptation addresses the problem of accuracy drop that a classifier may suffer when the training data (source domain) and the testing data (target domain) are drawn from different distributions. In this work, we focus on domain adaptation for structured SVM (SSVM). We propose a cost-sensitive domain adaptation method for SSVM, namely COSS-SSVM. In particular, during the re-training of an adapted classifier based on target and source data, the idea that we explore consists in introducing a non-zero cost even for correctly classified source domain samples. Eventually, we aim to learn a more targetoriented classifier by not rewarding (zero loss) properly classified source-domain training samples. We assess the effectiveness of COSS-SSVM on multi-category object recognition. |
|
|
Address |
Stockholm; Sweden; August 2014 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
1051-4651 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICPR |
|
|
Notes |
ADAS; 600.057; 600.054; 601.217; 600.076 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ XRV2014a |
Serial |
2434 |
|
Permanent link to this record |
|
|
|
|
Author |
Jiaolong Xu; Sebastian Ramos; Xu Hu; David Vazquez; Antonio Lopez |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Multi-task Bilinear Classifiers for Visual Domain Adaptation |
Type |
Conference Article |
|
Year |
2013 |
Publication |
Advances in Neural Information Processing Systems Workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Domain Adaptation; Pedestrian Detection; ADAS |
|
|
Abstract |
We propose a method that aims to lessen the significant accuracy degradation
that a discriminative classifier can suffer when it is trained in a specific domain (source domain) and applied in a different one (target domain). The principal reason for this degradation is the discrepancies in the distribution of the features that feed the classifier in different domains. Therefore, we propose a domain adaptation method that maps the features from the different domains into a common subspace and learns a discriminative domain-invariant classifier within it. Our algorithm combines bilinear classifiers and multi-task learning for domain adaptation.
The bilinear classifier encodes the feature transformation and classification
parameters by a matrix decomposition. In this way, specific feature transformations for multiple domains and a shared classifier are jointly learned in a multi-task learning framework. Focusing on domain adaptation for visual object detection, we apply this method to the state-of-the-art deformable part-based model for cross domain pedestrian detection. Experimental results show that our method significantly avoids the domain drift and improves the accuracy when compared to several baselines. |
|
|
Address |
Lake Tahoe; Nevada; USA; December 2013 |
|
|
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 |
NIPSW |
|
|
Notes |
ADAS; 600.054; 600.057; 601.217;ISE |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ XRH2013 |
Serial |
2340 |
|
Permanent link to this record |
|
|
|
|
Author |
J. Weickert; Bart M. Ter Haar Romeny; Antonio Lopez; W. Van Enk |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Orientation Analysis by Coherence-Enhancing Diffusion. |
Type |
Miscellaneous |
|
Year |
1997 |
Publication |
Proc. of the Real World Computing Symposium. |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
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 |
ADAS |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ WTL1997 |
Serial |
211 |
|
Permanent link to this record |
|
|
|
|
Author |
David Vazquez; Jiaolong Xu; Sebastian Ramos; Antonio Lopez; Daniel Ponsa |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes |
Type |
Conference Article |
|
Year |
2013 |
Publication |
CVPR Workshop on Ground Truth – What is a good dataset? |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
706 - 711 |
|
|
Keywords |
Pedestrian Detection; Domain Adaptation |
|
|
Abstract |
Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs. |
|
|
Address |
Portland; Oregon; June 2013 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
|
Language |
English |
Summary Language |
English |
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
CVPRW |
|
|
Notes |
ADAS; 600.054; 600.057; 601.217 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ VXR2013a |
Serial |
2219 |
|
Permanent link to this record |
|
|
|
|
Author |
David Vazquez; Javier Marin; Antonio Lopez; Daniel Ponsa; David Geronimo |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Virtual and Real World Adaptation for Pedestrian Detection |
Type |
Journal Article |
|
Year |
2014 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
|
Volume |
36 |
Issue |
4 |
Pages |
797-809 |
|
|
Keywords |
Domain Adaptation; Pedestrian Detection |
|
|
Abstract |
Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the dataset shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection accuracy than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector. |
|
|
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 |
0162-8828 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
ADAS; 600.057; 600.054; 600.076 |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ VML2014 |
Serial |
2275 |
|
Permanent link to this record |
|
|
|
|
Author |
David Vazquez; Antonio Lopez; Daniel Ponsa |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Unsupervised Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection |
Type |
Conference Article |
|
Year |
2012 |
Publication |
21st International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
3492 - 3495 |
|
|
Keywords |
Pedestrian Detection; Domain Adaptation; Virtual worlds |
|
|
Abstract |
Vision-based object detectors are crucial for different applications. They rely on learnt object models. Ideally, we would like to deploy our vision system in the scenario where it must operate, and lead it to self-learn how to distinguish the objects of interest, i.e., without human intervention. However, the learning of each object model requires labelled samples collected through a tiresome manual process. For instance, we are interested in exploring the self-training of a pedestrian detector for driver assistance systems. Our first approach to avoid manual labelling consisted in the use of samples coming from realistic computer graphics, so that their labels are automatically available [12]. This would make possible the desired self-training of our pedestrian detector. However, as we showed in [14], between virtual and real worlds it may be a dataset shift. In order to overcome it, we propose the use of unsupervised domain adaptation techniques that avoid human intervention during the adaptation process. In particular, this paper explores the use of the transductive SVM (T-SVM) learning algorithm in order to adapt virtual and real worlds for pedestrian detection (Fig. 1). |
|
|
Address |
Tsukuba Science City, Japan |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
IEEE |
Place of Publication |
Tsukuba Science City, JAPAN |
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
1051-4651 |
ISBN |
978-1-4673-2216-4 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICPR |
|
|
Notes |
ADAS |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ VLP2012 |
Serial |
1981 |
|
Permanent link to this record |
|
|
|
|
Author |
David Vazquez; Antonio Lopez; Daniel Ponsa; Javier Marin |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Cool world: domain adaptation of virtual and real worlds for human detection using active learning |
Type |
Conference Article |
|
Year |
2011 |
Publication |
NIPS Domain Adaptation Workshop: Theory and Application |
Abbreviated Journal |
NIPS-DA |
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Pedestrian Detection; Virtual; Domain Adaptation; Active Learning |
|
|
Abstract |
Image based human detection is of paramount interest for different applications. The most promising human detectors rely on discriminatively learnt classifiers, i.e., trained with labelled samples. However, labelling is a manual intensive task, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, in Marin et al. we have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera and the same type of scenario. Accordingly, in Vazquez et al. we cast the problem as one of supervised domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we use an active learning technique. Thus, ultimately our human model is learnt by the combination of virtual- and real-world labelled samples which, to the best of our knowledge, was not done before. Here, we term such combined space cool world. In this extended abstract we summarize our proposal, and include quantitative results from Vazquez et al. showing its validity. |
|
|
Address |
Granada, Spain |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
Granada, Spain |
Editor |
|
|
|
Language |
English |
Summary Language |
English |
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
DA-NIPS |
|
|
Notes |
ADAS |
Approved |
no |
|
|
Call Number ![sorted by Call Number field, descending order (down)](img/sort_desc.gif) |
ADAS @ adas @ VLP2011b |
Serial |
1756 |
|
Permanent link to this record |