93 citations · 446 across the 32 of their papers we have counts for
3 papers · 1 filter
On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints
Damien Teney, Ehsan Abbasnejad, Anton van den Hengel
The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised tra…
V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices
Damien Teney, Peng Wang, Jiewei Cao +3
One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over…
Actively Seeking and Learning from Live Data
Damien Teney, Anton van den Hengel
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 p…