UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations

Abbas, A; Andreopoulos, Y; (2020) Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations. IEEE Transactions on Image Processing , 29 pp. 7656-7667. 10.1109/TIP.2020.3005508. Green open access

[img]
Preview
Text
tip_bmoe_v7_final.pdf - Accepted version

Download (2MB) | Preview

Abstract

We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem. To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.

Type: Article
Title: Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/TIP.2020.3005508
Publisher version: https://doi.org/10.1109/TIP.2020.3005508
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Mixtures of experts , constrained data transfer , single shot object detection , single image super resolution , realtime action classification
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10107986
Downloads since deposit
16Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item