Abstract
Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for all perceptual problems together, solving them efficiently and coherently in an integrated manner. In order to capture some of these advantages in machine perception, we ask two questions: whether deep neural networks can learn universal image representations, useful not only for a single task but for all of them, and how the solutions to the different tasks can be integrated in this framework. We answer by proposing a new architecture, which we call multinet, in which not only deep image features are shared between tasks, but where tasks can interact in a recurrent manner by encoding the results of their analysis in a common shared representation of the data. In this manner, we show that the performance of individual tasks in standard benchmarks can be improved first by sharing features between them and then, more significantly, by integrating their solutions in the common representation.
Original language | English |
---|---|
Title of host publication | NIPS'16 Proceedings of the 30th International Conference on Neural Information Processing Systems |
Place of Publication | Barcelona, Spain |
Publisher | ACM |
Pages | 235-243 |
Number of pages | 9 |
ISBN (Electronic) | 978-1-5108-3881-9 |
Publication status | Published - 5 Dec 2016 |
Event | 30th Annual Conference on Neural Information Processing Systems - Barcelona, Spain Duration: 5 Dec 2016 → 10 Dec 2016 https://nips.cc/Conferences/2016 |
Conference
Conference | 30th Annual Conference on Neural Information Processing Systems |
---|---|
Abbreviated title | NIPS 2016 |
Country/Territory | Spain |
City | Barcelona |
Period | 5/12/16 → 10/12/16 |
Internet address |
Fingerprint
Dive into the research topics of 'Integrated Perception with Recurrent Multi-Task Neural Networks'. Together they form a unique fingerprint.Profiles
-
Hakan Bilen
- School of Informatics - Reader
- Institute of Perception, Action and Behaviour
- Language, Interaction, and Robotics
Person: Academic: Research Active