Actively Seeking and Learning From Live Data

Damien Teney, Anton van den Hengel; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1940-1949


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 VQA-CP 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.

Related Material

[pdf] [supp]
author = {Teney, Damien and van den Hengel, Anton},
title = {Actively Seeking and Learning From Live Data},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}