Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/126704
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Actively seeking and learning from live data |
Author: | Teney, D. Hengel, A.V.D. |
Citation: | Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, vol.2019-June, pp.1940-1949 |
Publisher: | Computer Vision Foundation / IEEE |
Publisher Place: | online |
Issue Date: | 2019 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 9781728132938 |
ISSN: | 1063-6919 2575-7075 |
Conference Name: | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (15 Jun 2019 - 20 Jun 2019 : Long Beach, USA) |
Statement of Responsibility: | Damien Teney, Anton van den Hengel |
Abstract: | One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned. This is a particular problem for visual question answering methods, which may be asked questions about virtually anything. The approach we propose is a step toward overcoming this limitation by searching for the information required at test time. The resulting method dynamically utilizes data from an external source, such as a large set of questions/answers or images/captions. Concretely, we learn a set of base weights for a simple VQA model, that are specifically adapted to a given question with the information specifically retrieved for this question. The adaptation process leverages recent advances in gradient-based meta learning and contributions for efficient retrieval and cross-domain adaptation. We surpass the state-of-the-art on the VQACP v2 benchmark and demonstrate our approach to be intrinsically more robust to out-of-distribution test data. We demonstrate the use of external non-VQA data using the MS COCO captioning dataset to support the answering process. This approach opens a new avenue for open-domain VQA systems that interface with diverse sources of data. |
Rights: | ©2019 IEEE |
DOI: | 10.1109/CVPR.2019.00204 |
Published version: | http://openaccess.thecvf.com/CVPR2019.py |
Appears in Collections: | Aurora harvest 8 Australian Institute for Machine Learning publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.