|
Records |
Links |
|
Author |
Victor Ponce; Baiyu Chen; Marc Oliu; Ciprian Corneanu; Albert Clapes; Isabelle Guyon; Xavier Baro; Hugo Jair Escalante; Sergio Escalera |
|
|
Title |
ChaLearn LAP 2016: First Round Challenge on First Impressions – Dataset and Results |
Type |
Conference Article |
|
Year |
2016 |
Publication |
14th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Behavior Analysis; Personality Traits; First Impressions |
|
|
Abstract |
This paper summarizes the ChaLearn Looking at People 2016 First Impressions challenge data and results obtained by the teams in the rst round of the competition. The goal of the competition was to automatically evaluate ve \apparent“ personality traits (the so-called \Big Five”) from videos of subjects speaking in front of a camera, by using human judgment. In this edition of the ChaLearn challenge, a novel data set consisting of 10,000 shorts clips from YouTube videos has been made publicly available. The ground truth for personality traits was obtained from workers of Amazon Mechanical Turk (AMT). To alleviate calibration problems between workers, we used pairwise comparisons between videos, and variable levels were reconstructed by tting a Bradley-Terry-Luce model with maximum likelihood. The CodaLab open source
platform was used for submission of predictions and scoring. The competition attracted, over a period of 2 months, 84 participants who are grouped in several teams. Nine teams entered the nal phase. Despite the diculty of the task, the teams made great advances in this round of the challenge. |
|
|
Address |
Amsterdam; The Netherlands; October 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 |
ECCVW |
|
|
Notes |
HuPBA;MV; 600.063 |
Approved |
no |
|
|
Call Number |
Admin @ si @ PCP2016 |
Serial |
2828 |
|
Permanent link to this record |
|
|
|
|
Author |
Cesar de Souza; Adrien Gaidon; Eleonora Vig; Antonio Lopez |
|
|
Title |
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition |
Type |
Conference Article |
|
Year |
2016 |
Publication |
14th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
697-716 |
|
|
Keywords |
|
|
|
Abstract |
Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos. |
|
|
Address |
Amsterdam; The Netherlands; October 2016 |
|
|
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 |
ECCV |
|
|
Notes |
ADAS; 600.076; 600.085 |
Approved |
no |
|
|
Call Number |
Admin @ si @ SGV2016 |
Serial |
2824 |
|
Permanent link to this record |
|
|
|
|
Author |
Baiyu Chen; Sergio Escalera; Isabelle Guyon; Victor Ponce; N. Shah; Marc Oliu |
|
|
Title |
Overcoming Calibration Problems in Pattern Labeling with Pairwise Ratings: Application to Personality Traits |
Type |
Conference Article |
|
Year |
2016 |
Publication |
14th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Calibration of labels; Label bias; Ordinal labeling; Variance Models; Bradley-Terry-Luce model; Continuous labels; Regression; Personality traits; Crowd-sourced labels |
|
|
Abstract |
We address the problem of calibration of workers whose task is to label patterns with continuous variables, which arises for instance in labeling images of videos of humans with continuous traits. Worker bias is particularly dicult to evaluate and correct when many workers contribute just a few labels, a situation arising typically when labeling is crowd-sourced. In the scenario of labeling short videos of people facing a camera with personality traits, we evaluate the feasibility of the pairwise ranking method to alleviate bias problems. Workers are exposed to pairs of videos at a time and must order by preference. The variable levels are reconstructed by fitting a Bradley-Terry-Luce model with maximum likelihood. This method may at first sight, seem prohibitively expensive because for N videos, p = N (N-1)/2 pairs must be potentially processed by workers rather that N videos. However, by performing extensive simulations, we determine an empirical law for the scaling of the number of pairs needed as a function of the number of videos in order to achieve a given accuracy of score reconstruction and show that the pairwise method is a ordable. We apply the method to the labeling of a large scale dataset of 10,000 videos used in the ChaLearn Apparent Personality Trait challenge. |
|
|
Address |
Amsterdam; The Netherlands; October 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 |
ECCVW |
|
|
Notes |
HuPBA;MILAB; |
Approved |
no |
|
|
Call Number |
Admin @ si @ CEG2016 |
Serial |
2829 |
|
Permanent link to this record |
|
|
|
|
Author |
Iiris Lusi; Sergio Escalera; Gholamreza Anbarjafari |
|
|
Title |
SASE: RGB-Depth Database for Human Head Pose Estimation |
Type |
Conference Article |
|
Year |
2016 |
Publication |
14th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Slides |
|
|
Address |
Amsterdam; The Netherlands; October 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 |
ECCVW |
|
|
Notes |
HuPBA;MILAB; |
Approved |
no |
|
|
Call Number |
Admin @ si @ LEA2016a |
Serial |
2840 |
|
Permanent link to this record |
|
|
|
|
Author |
Saad Minhas; Aura Hernandez-Sabate; Shoaib Ehsan; Katerine Diaz; Ales Leonardis; Antonio Lopez; Klaus McDonald Maier |
|
|
Title |
LEE: A photorealistic Virtual Environment for Assessing Driver-Vehicle Interactions in Self-Driving Mode |
Type |
Conference Article |
|
Year |
2016 |
Publication |
14th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
9915 |
Issue |
|
Pages |
894-900 |
|
|
Keywords |
Simulation environment; Automated Driving; Driver-Vehicle interaction |
|
|
Abstract |
Photorealistic virtual environments are crucial for developing and testing automated driving systems in a safe way during trials. As commercially available simulators are expensive and bulky, this paper presents a low-cost, extendable, and easy-to-use (LEE) virtual environment with the aim to highlight its utility for level 3 driving automation. In particular, an experiment is performed using the presented simulator to explore the influence of different variables regarding control transfer of the car after the system was driving autonomously in a highway scenario. The results show that the speed of the car at the time when the system needs to transfer the control to the human driver is critical. |
|
|
Address |
Amsterdam; The Netherlands; October 2016 |
|
|
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 |
ECCVW |
|
|
Notes |
ADAS;IAM; 600.085; 600.076 |
Approved |
no |
|
|
Call Number |
MHE2016 |
Serial |
2865 |
|
Permanent link to this record |
|
|
|
|
Author |
Eugenio Alcala; Laura Sellart; Vicenc Puig; Joseba Quevedo; Jordi Saludes; David Vazquez; Antonio Lopez |
|
|
Title |
Comparison of two non-linear model-based control strategies for autonomous vehicles |
Type |
Conference Article |
|
Year |
2016 |
Publication |
24th Mediterranean Conference on Control and Automation |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
846-851 |
|
|
Keywords |
Autonomous Driving; Control |
|
|
Abstract |
This paper presents the comparison of two nonlinear model-based control strategies for autonomous cars. A control oriented model of vehicle based on a bicycle model is used. The two control strategies use a model reference approach. Using this approach, the error dynamics model is developed. Both controllers receive as input the longitudinal, lateral and orientation errors generating as control outputs the steering angle and the velocity of the vehicle. The first control approach is based on a non-linear control law that is designed by means of the Lyapunov direct approach. The second approach is based on a sliding mode-control that defines a set of sliding surfaces over which the error trajectories will converge. The main advantage of the sliding-control technique is the robustness against non-linearities and parametric uncertainties in the model. However, the main drawback of first order sliding mode is the chattering, so it has been implemented a high order sliding mode control. To test and compare the proposed control strategies, different path following scenarios are used in simulation. |
|
|
Address |
Athens; Greece; 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 |
MED |
|
|
Notes |
ADAS; 600.085; 600.082; 600.076 |
Approved |
no |
|
|
Call Number |
ADAS @ adas @ ASP2016 |
Serial |
2750 |
|
Permanent link to this record |
|
|
|
|
Author |
Jose Marone; Simone Balocco; Marc Bolaños; Jose Massa; Petia Radeva |
|
|
Title |
Learning the Lumen Border using a Convolutional Neural Networks classifier |
Type |
Conference Article |
|
Year |
2016 |
Publication |
19th International Conference on Medical Image Computing and Computer Assisted Intervention Workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
IntraVascular UltraSound (IVUS) is a technique allowing the diagnosis of coronary plaque. An accurate (semi-)automatic assessment of the luminal contours could speed up the diagnosis. In most of the approaches, the information on the vessel shape is obtained combining a supervised learning step with a local refinement algorithm. In this paper, we explore for the first time, the use of a Convolutional Neural Networks (CNN) architecture that on one hand is able to extract the optimal image features and at the same time can serve as a supervised classifier to detect the lumen border in IVUS images. The main limitation of CNN, relies on the fact that this technique requires a large amount of training data due to the huge amount of parameters that it has. To
solve this issue, we introduce a patch classification approach to generate an extended training-set from a few annotated images. An accuracy of 93% and F-score of 71% was obtained with this technique, even when it was applied to challenging frames containig calcified plaques, stents and catheter shadows. |
|
|
Address |
Athens; Greece; October 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 |
MICCAIW |
|
|
Notes |
MILAB; |
Approved |
no |
|
|
Call Number |
Admin @ si @ MBB2016 |
Serial |
2822 |
|
Permanent link to this record |
|
|
|
|
Author |
Antonio Esteban Lansaque; Carles Sanchez; Agnes Borras; Marta Diez-Ferrer; Antoni Rosell; Debora Gil |
|
|
Title |
Stable Anatomical Structure Tracking for video-bronchoscopy Navigation |
Type |
Conference Article |
|
Year |
2016 |
Publication |
19th International Conference on Medical Image Computing and Computer Assisted Intervention Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Lung cancer diagnosis; video-bronchoscopy; airway lumen detection; region tracking |
|
|
Abstract |
Bronchoscopy allows to examine the patient airways for detection of lesions and sampling of tissues without surgery. A main drawback in lung cancer diagnosis is the diculty to check whether the exploration is following the correct path to the nodule that has to be biopsied. The most extended guidance uses uoroscopy which implies repeated radiation of clinical sta and patients. Alternatives such as virtual bronchoscopy or electromagnetic navigation are very expensive and not completely robust to blood, mocus or deformations as to be extensively used. We propose a method that extracts and tracks stable lumen regions at dierent levels of the bronchial tree. The tracked regions are stored in a tree that encodes the anatomical structure of the scene which can be useful to retrieve the path to the lesion that the clinician should follow to do the biopsy. We present a multi-expert validation of our anatomical landmark extraction in 3 intra-operative ultrathin explorations. |
|
|
Address |
Athens; Greece; October 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 |
MICCAIW |
|
|
Notes |
IAM; 600.075 |
Approved |
no |
|
|
Call Number |
Admin @ si @ LSB2016b |
Serial |
2857 |
|
Permanent link to this record |
|
|
|
|
Author |
Antoni Gurgui; Debora Gil; Enric Marti; Vicente Grau |
|
|
Title |
Left-Ventricle Basal Region Constrained Parametric Mapping to Unitary Domain |
Type |
Conference Article |
|
Year |
2016 |
Publication |
7th International Workshop on Statistical Atlases & Computational Modelling of the Heart |
Abbreviated Journal |
|
|
|
Volume |
10124 |
Issue |
|
Pages |
163-171 |
|
|
Keywords |
Laplacian; Constrained maps; Parameterization; Basal ring |
|
|
Abstract |
Due to its complex geometry, the basal ring is often omitted when putting different heart geometries into correspondence. In this paper, we present the first results on a new mapping of the left ventricle basal rings onto a normalized coordinate system using a fold-over free approach to the solution to the Laplacian. To guarantee correspondences between different basal rings, we imposed some internal constrained positions at anatomical landmarks in the normalized coordinate system. To prevent internal fold-overs, constraints are handled by cutting the volume into regions defined by anatomical features and mapping each piece of the volume separately. Initial results presented in this paper indicate that our method is able to handle internal constrains without introducing fold-overs and thus guarantees one-to-one mappings between different basal ring geometries. |
|
|
Address |
Athens; October 2016 |
|
|
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 |
STACOM |
|
|
Notes |
IAM; |
Approved |
no |
|
|
Call Number |
Admin @ si @ GGM2016 |
Serial |
2884 |
|
Permanent link to this record |
|
|
|
|
Author |
Petia Radeva |
|
|
Title |
Can Deep Learning and Egocentric Vision for Visual Lifelogging Help Us Eat Better? |
Type |
Conference Article |
|
Year |
2016 |
Publication |
19th International Conference of the Catalan Association for Artificial Intelligence |
Abbreviated Journal |
|
|
|
Volume |
4 |
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona; October 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 |
CCIA |
|
|
Notes |
MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ Rad2016 |
Serial |
2832 |
|
Permanent link to this record |
|
|
|
|
Author |
Alvaro Peris; Marc Bolaños; Petia Radeva; Francisco Casacuberta |
|
|
Title |
Video Description Using Bidirectional Recurrent Neural Networks |
Type |
Conference Article |
|
Year |
2016 |
Publication |
25th International Conference on Artificial Neural Networks |
Abbreviated Journal |
|
|
|
Volume |
2 |
Issue |
|
Pages |
3-11 |
|
|
Keywords |
Video description; Neural Machine Translation; Birectional Recurrent Neural Networks; LSTM; Convolutional Neural Networks |
|
|
Abstract |
Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames. |
|
|
Address |
Barcelona; September 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 |
ICANN |
|
|
Notes |
MILAB; |
Approved |
no |
|
|
Call Number |
Admin @ si @ PBR2016 |
Serial |
2833 |
|
Permanent link to this record |
|
|
|
|
Author |
Fernando Vilariño; Dan Norton; Onur Ferhat |
|
|
Title |
The Eye Doesn't Click – Eyetracking and Digital Content Interaction |
Type |
Conference Article |
|
Year |
2016 |
Publication |
4S/EASST Conference |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona; Spain; September 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 |
EASST |
|
|
Notes |
MV; 600.097;SIAI |
Approved |
no |
|
|
Call Number |
Admin @ si @VNF2016 |
Serial |
2801 |
|
Permanent link to this record |
|
|
|
|
Author |
Ivet Rafegas; Maria Vanrell |
|
|
Title |
Colour Visual Coding in trained Deep Neural Networks |
Type |
Abstract |
|
Year |
2016 |
Publication |
European Conference on Visual Perception |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona; Spain; August 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 |
ECVP |
|
|
Notes |
CIC |
Approved |
no |
|
|
Call Number |
Admin @ si @ RaV2016b |
Serial |
2895 |
|
Permanent link to this record |
|
|
|
|
Author |
Arash Akbarinia; C. Alejandro Parraga |
|
|
Title |
Dynamically Adjusted Surround Contrast Enhances Boundary Detection, European Conference on Visual Perception |
Type |
Conference Article |
|
Year |
2016 |
Publication |
European Conference on Visual Perception |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona; Spain; August 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 |
ECVP |
|
|
Notes |
NEUROBIT |
Approved |
no |
|
|
Call Number |
Admin @ si @ AkP2016b |
Serial |
2900 |
|
Permanent link to this record |
|
|
|
|
Author |
Yaxing Wang; L. Zhang; Joost Van de Weijer |
|
|
Title |
Ensembles of generative adversarial networks |
Type |
Conference Article |
|
Year |
2016 |
Publication |
30th Annual Conference on Neural Information Processing Systems Worshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Ensembles are a popular way to improve results of discriminative CNNs. The
combination of several networks trained starting from different initializations
improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways to construct ensembles. The first one is based on the fact that in the minimax game which is played to optimize the GAN objective the generator network keeps on changing even after the network can be considered optimal. As such ensembles of GANs can be constructed based on the same network initialization but just taking models which have different amount of iterations. These so-called self ensembles are much faster to train than traditional ensembles. The second method, called cascade GANs, redirects part of the training data which is badly modeled by the first GAN to another GAN. In experiments on the CIFAR10 dataset we show that ensembles of GANs obtain model probability distributions which better model the data distribution. In addition, we show that these improved results can be obtained at little additional computational cost. |
|
|
Address |
Barcelona; Spain; 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 |
NIPSW |
|
|
Notes |
LAMP; 600.068 |
Approved |
no |
|
|
Call Number |
Admin @ si @ WZW2016 |
Serial |
2905 |
|
Permanent link to this record |