| Elliot Crowley and Joseph Cronin |
| Tue 01 Nov 2016, 11:00 - 12:00 |
| IF 4.31/4.33 |
If you have a question about this talk, please contact: Gareth Beedham (gbeedham)
Elliot Crowley
“The Art of Detection”
The objective of this work is to recognize object categories in paintings, such as cars, cows and cathedrals. We achieve this by training classifiers from natural images of the objects. We make the following contributions: (i) we measure the extent of the domain shift problem for image-level classifiers trained on natural images vs paintings, for a variety of CNN architectures; (ii) we demonstrate that classification- by-detection (i.e. learning classifiers for regions rather than the entire image) recognizes (and locates) a wide range of small objects in paintings that are not picked up by image-level classifiers, and combining these two methods improves performance; and (iii) we develop a system that learns a region-level classifier on-the-fly for an object category of a user’s choosing, which is then applied to over 60 million object regions across 210,000 paintings to retrieve localised instances of that category.
Joseph Cronin
“Rescaling Spike Pattern Probabilities with Energy Based Models”
Studying multi-neuron firing patterns is essential for the understanding of coding, plasticity and learning in the brain. We examine the use of energy based models for capturing these multi-neuron firing distributions, specifically in the case of recently examined simulated & recorded data where we found firing rates of individual neurons dominated the captured correlation structure. We discuss an attempt to solve this issue through the rescaling of pattern probabilities using the independent model.