← Search

Simon J.D. Prince

2 accepted papers

2021

Optimizing Deeper Transformers on Small Datasets

ACL 2021long

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with p…

2015

Modeling Object Appearance Using Context-Conditioned Component Analysis

CVPR 2015poster

Subspace models have been very successful at modeling the appearance of structured image datasets when the visual objects have been aligned in the images (e.g., faces). Even with extensions that allow for global transformations or dense warps of the image, the set of visual objects whose appearance…

Cited by 8SourcePDFScholar