|
Records |
Links |
|
Author |
Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez |
|
|
Title |
Factorization with Missing and Noisy Data |
Type |
Conference Article |
|
Year |
2006 |
Publication |
6th International Conference on Computational Science |
Abbreviated Journal |
ICCS´06 |
|
|
Volume |
LNCS 3991 |
Issue |
|
Pages |
555–562 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Reading (United Kingdom) |
|
|
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 |
ADAS @ adas @ JSL2006b |
Serial |
653 |
|
Permanent link to this record |
|
|
|
|
Author |
Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez |
|
|
Title |
An Iterative Multiresolution Scheme for SFM |
Type |
Conference Article |
|
Year |
2006 |
Publication |
International Conference on Image Analysis and Recognition |
Abbreviated Journal |
ICIAR 2006 |
|
|
Volume |
LNCS 4141 |
Issue |
1 |
Pages |
804–815 |
|
|
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 |
ADAS @ adas @ JSL2006c |
Serial |
704 |
|
Permanent link to this record |
|
|
|
|
Author |
Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez |
|
|
Title |
Motion Segmentation from Feature Trajectories with Missing Data |
Type |
Conference Article |
|
Year |
2007 |
Publication |
3rd. Iberian Conference on Pattern Recognition and Image Analysis |
Abbreviated Journal |
IbPRIA 2007 |
|
|
Volume |
LNCS 4477 |
Issue |
|
Pages |
483–490 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Girona (Spain) |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
J. Marti et al. (Eds.) |
|
|
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 |
ADAS @ adas @ JSL2007a |
Serial |
814 |
|
Permanent link to this record |
|
|
|
|
Author |
Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez |
|
|
Title |
An Adapted Alternation Approach for Recommender Systems |
Type |
Conference Article |
|
Year |
2008 |
Publication |
IEEE International Conference on e–Business Engineering, |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
128–135 |
|
|
Keywords |
|
|
|
Abstract |
This paper presents an adaptation of the alternation technique to tackle the prediction task in recommender systems. These systems are widely considered in electronic commerce to help customers to find products they will probably like or dislike. As the SVD-based approaches, the proposed adapted alternation technique uses all the information stored in the system to find the predictions. The main advantage of this technique with respect to the SVD-based ones is that it can deal with missing data. Furthermore, it has a smaller computational cost. Experimental results with public data sets are provided in order to show the viability of the proposed adapted alternation approach. |
|
|
Address |
Xi’an (Xina) |
|
|
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 |
ADAS @ adas @ JSL2008e |
Serial |
1044 |
|
Permanent link to this record |
|
|
|
|
Author |
Carola Figueroa Flores; Bogdan Raducanu; David Berga; Joost Van de Weijer |
|
|
Title |
Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains |
Type |
Conference Article |
|
Year |
2021 |
Publication |
16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Abbreviated Journal |
|
|
|
Volume |
4 |
Issue |
|
Pages |
163-171 |
|
|
Keywords |
|
|
|
Abstract |
arXiv:2007.12562
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which does not require explicit saliency maps to improve image classification, but they are learned implicitely, during the training of an end-to-end image classification task. We show that our approach obtains similar results as the case when the saliency maps are provided explicitely. Combining RGB data with saliency maps represents a significant advantage for object recognition, especially for the case when training data is limited. We validate our method on several datasets for fine-grained classification tasks (Flowers, Birds and Cars). In addition, we show that our saliency estimation method, which is trained without any saliency groundtruth data, obtains competitive results on real image saliency benchmark (Toronto), and outperforms deep saliency models with synthetic images (SID4VAM). |
|
|
Address |
Virtual; February 2021 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
VISAPP |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ FRB2021c |
Serial |
3540 |
|
Permanent link to this record |
|
|
|
|
Author |
Carolina Malagelada; F.De Lorio; Fernando Azpiroz; Santiago Segui; Petia Radeva; Anna Accarino; J.Santos; Juan R. Malagelada |
|
|
Title |
Intestinal Dysmotility in Patients with Functional Intestinal Disorders Demonstrated by Computer Vision Analysis of Capsule Endoscopy Images |
Type |
Conference Article |
|
Year |
2010 |
Publication |
18th United European Gastroenterology Week |
Abbreviated Journal |
|
|
|
Volume |
56 |
Issue |
3 |
Pages |
A19-20 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
UEGW |
|
|
Notes |
MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ MLA2010 |
Serial |
1779 |
|
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 |
Cesar de Souza; Adrien Gaidon; Yohann Cabon; Antonio Lopez |
|
|
Title |
Procedural Generation of Videos to Train Deep Action Recognition Networks |
Type |
Conference Article |
|
Year |
2017 |
Publication |
30th IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
2594-2604 |
|
|
Keywords |
|
|
|
Abstract |
Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos. |
|
|
Address |
Honolulu; Hawaii; July 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 |
CVPR |
|
|
Notes |
ADAS; 600.076; 600.085; 600.118 |
Approved |
no |
|
|
Call Number |
Admin @ si @ SGC2017 |
Serial |
3051 |
|
Permanent link to this record |
|
|
|
|
Author |
Cesar Isaza; Joaquin Salas; Bogdan Raducanu |
|
|
Title |
Toward the Detection of Urban Infrastructures Edge Shadows |
Type |
Conference Article |
|
Year |
2010 |
Publication |
12th International Conference on Advanced Concepts for Intelligent Vision Systems |
Abbreviated Journal |
|
|
|
Volume |
6474 |
Issue |
I |
Pages |
30–37 |
|
|
Keywords |
|
|
|
Abstract |
In this paper, we propose a novel technique to detect the shadows cast by urban infrastructure, such as buildings, billboards, and traffic signs, using a sequence of images taken from a fixed camera. In our approach, we compute two different background models in parallel: one for the edges and one for the reflected light intensity. An algorithm is proposed to train the system to distinguish between moving edges in general and edges that belong to static objects, creating an edge background model. Then, during operation, a background intensity model allow us to separate between moving and static objects. Those edges included in the moving objects and those that belong to the edge background model are subtracted from the current image edges. The remaining edges are the ones cast by urban infrastructure. Our method is tested on a typical crossroad scene and the results show that the approach is sound and promising. |
|
|
Address |
Sydney, Australia |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
Springer Berlin Heidelberg |
Place of Publication |
|
Editor |
eds. Blanc–Talon et al |
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
0302-9743 |
ISBN |
978-3-642-17687-6 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ACIVS |
|
|
Notes |
OR;MV |
Approved |
no |
|
|
Call Number |
BCNPCL @ bcnpcl @ ISR2010 |
Serial |
1458 |
|
Permanent link to this record |
|
|
|
|
Author |
Cesar Isaza; Joaquin Salas; Bogdan Raducanu |
|
|
Title |
Synthetic ground truth dataset to detect shadow cast by static objects in outdoor |
Type |
Conference Article |
|
Year |
2012 |
Publication |
1st International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
art. 11 |
|
|
Keywords |
|
|
|
Abstract |
In this paper, we propose a precise synthetic ground truth dataset to study the problem of detection of the shadows cast by static objects in outdoor environments during extended periods of time (days). For our dataset, we have created a virtual scenario using a rendering software. To increase the realism of the simulated environment, we have defined the scenario in a precise geographical location. In our dataset the sun is by far the main illumination source. The sun position during the simulation time takes into consideration factors related to the geographical location, such as the latitude, longitude, elevation above sea level, and precise image capturing day and time. In our simulation the camera remains fixed. The dataset consists of seven days of simulation, from 10:00am to 5:00pm. Images are captured every 10 seconds. The shadows' ground truth is automatically computed by the rendering software. |
|
|
Address |
Capri, Italy |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
ACM |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
978-1-4503-1405-3 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
VIGTA |
|
|
Notes |
OR;MV |
Approved |
no |
|
|
Call Number |
Admin @ si @ ISR2012a |
Serial |
2037 |
|
Permanent link to this record |
|
|
|
|
Author |
Chee-Kheng Chng; Yuliang Liu; Yipeng Sun; Chun Chet Ng; Canjie Luo; Zihan Ni; ChuanMing Fang; Shuaitao Zhang; Junyu Han; Errui Ding; Jingtuo Liu; Dimosthenis Karatzas; Chee Seng Chan; Lianwen Jin |
|
|
Title |
ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT |
Type |
Conference Article |
|
Year |
2019 |
Publication |
15th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
1571-1576 |
|
|
Keywords |
|
|
|
Abstract |
This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT that consists of three major challenges: i) scene text detection, ii) scene text recognition, and iii) scene text spotting. A total of 78 submissions from 46 unique teams/individuals were received for this competition. The top performing score of each challenge is as follows: i) T1 – 82.65%, ii) T2.1 – 74.3%, iii) T2.2 – 85.32%, iv) T3.1 – 53.86%, and v) T3.2 – 54.91%. Apart from the results, this paper also details the ArT dataset, tasks description, evaluation metrics and participants' methods. The dataset, the evaluation kit as well as the results are publicly available at the challenge website. |
|
|
Address |
Sydney; Australia; September 2019 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICDAR |
|
|
Notes |
DAG; 600.121; 600.129 |
Approved |
no |
|
|
Call Number |
Admin @ si @ CLS2019 |
Serial |
3340 |
|
Permanent link to this record |
|
|
|
|
Author |
Chen Zhang; Maria del Mar Vila Muñoz; Petia Radeva; Roberto Elosua; Maria Grau; Angels Betriu; Elvira Fernandez-Giraldez; Laura Igual |
|
|
Title |
Carotid Artery Segmentation in Ultrasound Images |
Type |
Conference Article |
|
Year |
2015 |
Publication |
Computing and Visualization for Intravascular Imaging and Computer Assisted Stenting (CVII-STENT2015), Joint MICCAI Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Munich; Germany; October 2015 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
CVII-STENT |
|
|
Notes |
MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ ZVR2015 |
Serial |
2675 |
|
Permanent link to this record |
|
|
|
|
Author |
Chengyi Zou; Shuai Wan; Marta Mrak; Marc Gorriz Blanch; Luis Herranz; Tiannan Ji |
|
|
Title |
Towards Lightweight Neural Network-based Chroma Intra Prediction for Video Coding |
Type |
Conference Article |
|
Year |
2022 |
Publication |
29th IEEE International Conference on Image Processing |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Video coding; Quantization (signal); Computational modeling; Neural networks; Predictive models; Video compression; Syntactics |
|
|
Abstract |
In video compression the luma channel can be useful for predicting chroma channels (Cb, Cr), as has been demonstrated with the Cross-Component Linear Model (CCLM) used in Versatile Video Coding (VVC) standard. More recently, it has been shown that neural networks can even better capture the relationship among different channels. In this paper, a new attention-based neural network is proposed for cross-component intra prediction. With the goal to simplify neural network design, the new framework consists of four branches: boundary branch and luma branch for extracting features from reference samples, attention branch for fusing the first two branches, and prediction branch for computing the predicted chroma samples. The proposed scheme is integrated into VVC test model together with one additional binary block-level syntax flag which indicates whether a given block makes use of the proposed method. Experimental results demonstrate 0.31%/2.36%/2.00% BD-rate reductions on Y/Cb/Cr components, respectively, on top of the VVC Test Model (VTM) 7.0 which uses CCLM. |
|
|
Address |
Bordeaux; France; October 2022 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICIP |
|
|
Notes |
MACO |
Approved |
no |
|
|
Call Number |
Admin @ si @ ZWM2022 |
Serial |
3790 |
|
Permanent link to this record |
|
|
|
|
Author |
Chenshen Wu; Joost Van de Weijer |
|
|
Title |
Density Map Distillation for Incremental Object Counting |
Type |
Conference Article |
|
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
2505-2514 |
|
|
Keywords |
|
|
|
Abstract |
We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A naïve approach to incremental object counting would suffer from catastrophic forgetting, where it would suffer from a dramatic performance drop on previous tasks. In this paper, we propose a new exemplar-free functional regularization method, called Density Map Distillation (DMD). During training, we introduce a new counter head for each task and introduce a distillation loss to prevent forgetting of previous tasks. Additionally, we introduce a cross-task adaptor that projects the features of the current backbone to the previous backbone. This projector allows for the learning of new features while the backbone retains the relevant features for previous tasks. Finally, we set up experiments of incremental learning for counting new objects. Results confirm that our method greatly reduces catastrophic forgetting and outperforms existing methods. |
|
|
Address |
Vancouver; Canada; June 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 |
CVPRW |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ WuW2023 |
Serial |
3916 |
|
Permanent link to this record |
|
|
|
|
Author |
Chenshen Wu; Luis Herranz; Xialei Liu; Joost Van de Weijer; Bogdan Raducanu |
|
|
Title |
Memory Replay GANs: Learning to Generate New Categories without Forgetting |
Type |
Conference Article |
|
Year |
2018 |
Publication |
32nd Annual Conference on Neural Information Processing Systems |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
5966-5976 |
|
|
Keywords |
|
|
|
Abstract |
Previous works on sequential learning address the problem of forgetting in discriminative models. In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (ie forgetting). Addressing this problem, we propose Memory Replay GANs (MeRGANs), a conditional GAN framework that integrates a memory replay generator. We study two methods to prevent forgetting by leveraging these replays, namely joint training with replay and replay alignment. Qualitative and quantitative experimental results in MNIST, SVHN and LSUN datasets show that our memory replay approach can generate competitive images while significantly mitigating the forgetting of previous categories. |
|
|
Address |
Montreal; Canada; December 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 |
NIPS |
|
|
Notes |
LAMP; 600.106; 600.109; 602.200; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ WHL2018 |
Serial |
3249 |
|
Permanent link to this record |