Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/126704
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Teney, D. | - |
dc.contributor.author | Hengel, A.V.D. | - |
dc.date.issued | 2019 | - |
dc.identifier.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 | - |
dc.identifier.isbn | 9781728132938 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.issn | 2575-7075 | - |
dc.identifier.uri | http://hdl.handle.net/2440/126704 | - |
dc.description.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. | - |
dc.description.statementofresponsibility | Damien Teney, Anton van den Hengel | - |
dc.language.iso | en | - |
dc.publisher | Computer Vision Foundation / IEEE | - |
dc.relation.ispartofseries | IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.rights | ©2019 IEEE | - |
dc.source.uri | http://openaccess.thecvf.com/CVPR2019.py | - |
dc.title | Actively seeking and learning from live data | - |
dc.type | Conference paper | - |
dc.contributor.conference | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (15 Jun 2019 - 20 Jun 2019 : Long Beach, USA) | - |
dc.identifier.doi | 10.1109/CVPR.2019.00204 | - |
dc.publisher.place | online | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Teney, D. [0000-0003-2130-6650] | - |
dc.identifier.orcid | Hengel, A.V.D. [0000-0003-3027-8364] | - |
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.