Hakan Bilen
University of Edinburgh
108 Papers
752 Citations
Hakan Bilen is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 23, co-authored 86 publications. Previous affiliations of Hakan Bilen include Katholieke Universiteit Leuven & University of Oxford.
Chat about Author
Papers
Weakly Supervised Deep Detection Networks
Hakan Bilen,Andrea Vedaldi +1 more
- 01 Jun 2016
TL;DR: This paper proposes a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification.
Dynamic Image Networks for Action Recognition
Hakan Bilen,Basura Fernando,Efstratios Gavves,Andrea Vedaldi,Stephen Gould +4 more
- 27 Jun 2016
TL;DR: The new approximate rank pooling CNN layer allows the use of existing CNN models directly on video data with fine-tuning to generalize dynamic images to dynamic feature maps and the power of the new representations on standard benchmarks in action recognition achieving state-of-the-art performance.
745
Self-Supervised Video Representation Learning with Odd-One-Out Networks
Basura Fernando,Hakan Bilen,Efstratios Gavves,Stephen Gould +3 more
- 21 Jul 2017
TL;DR: A new self-supervised CNN pre-training technique based on a novel auxiliary task called odd-one-out learning, which learns temporal representations for videos that generalizes to other related tasks such as action recognition.
677
•Posted Content
Learning multiple visual domains with residual adapters
TL;DR: This paper develops a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains and introduces the Visual Decathlon Challenge, a benchmark that evaluates the ability of representations to capture simultaneously ten very differentVisual domains and measures their ability to recognize well uniformly.
646
•Posted Content
iDLG: Improved Deep Leakage from Gradients.
TL;DR: This paper finds that sharing gradients definitely leaks the ground-truth labels and proposes a simple but reliable approach to extract accurate data from the gradients, which is valid for any differentiable model trained with cross-entropy loss over one-hot labels and is named Improved DLG (iDLG).