Actively seeking and learning from live data

Simple item page
dc.contributor.authorTeney, D.
dc.contributor.authorHengel, A.V.D.
dc.contributor.conferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (15 Jun 2019 - 20 Jun 2019 : Long Beach, USA)
dc.date.issued2019
dc.description.abstractOne 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.statementofresponsibilityDamien Teney, Anton van den Hengel
dc.identifier.citationProceedings / 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.doi10.1109/CVPR.2019.00204
dc.identifier.isbn9781728132938
dc.identifier.issn1063-6919
dc.identifier.issn2575-7075
dc.identifier.orcidTeney, D. [0000-0003-2130-6650]
dc.identifier.orcidHengel, A.V.D. [0000-0003-3027-8364]
dc.identifier.urihttp://hdl.handle.net/2440/126704
dc.language.isoen
dc.publisherComputer Vision Foundation / IEEE
dc.publisher.placeonline
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rights©2019 IEEE
dc.source.urihttp://openaccess.thecvf.com/CVPR2019.py
dc.titleActively seeking and learning from live data
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications