Projects per year
We address this oversight by incorporating a context-adversarial component into the meta-learning process. This produces an initialisation which is both context-agnostic and task-generalised. We evaluate our approach on three commonly used meta-learning algorithms and four case studies. We demonstrate our context-agnostic meta-learning improves results in each case. First, we report few-shot character classification on the Omniglot dataset, using alphabets as context. An average improvement of 4.3% is observed across methods and tasks when classifying characters from an unseen alphabet. Second, we perform few-shot classification on Mini-ImageNet, obtaining context from the label hierarchy, with an average improvement of 2.8%. Third, we perform few-shot classificaiton on CUB, with annotation metadata as context, and demonstrate an average improvement of 1.9%. Fourth, we evaluate on a dataset for personalised energy expenditure predictions from video, using participant knowledge as context. We demonstrate that context-agnostic meta-learning decreases the average mean square error by 30%.
|Title of host publication||Asian Conference on Computer Vision|
|Publication status||Accepted/In press - 23 Sept 2020|
- Digital Health
FingerprintDive into the research topics of 'Meta-Learning with Context-Agnostic Initialisations'. Together they form a unique fingerprint.
Sadaf R Alam (Manager), Steven A Chapman (Manager), Polly E Eccleston (Other), Simon H Atack (Other) & D A G Williams (Manager)