BROWSE

Related Researcher

Author's Photo

Kim, Kwang In
Machine Learning and Vision Lab
Research Interests
  • Neural networks, semi-supervised learning; unsupervised learning; learning on Riemannian manifolds and graph-structured data; human body pose estimation; human hand pose estimation; image and video enhancement.

ITEM VIEW & DOWNLOAD

Improving predictors via combination across diverse task categories

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Improving predictors via combination across diverse task categories
Author
Kim, Kwang In
Issue Date
2021-07-20
Publisher
International Conference on Machine Learning
Citation
International Conference on Machine Learning
Abstract
Predictor combination is the problem of improving a task predictor using predictors of other tasks when the forms of individual predictors are unknown. Previous work approached this problem by nonparametrically assessing predictor relationships based on their joint evaluations on a shared sample. This limits their application to cases where all predictors are defined on the same task category, e.g. all predictors estimate attributes of shoes. We present a new predictor combination algorithm that overcomes this limitation. Our algorithm aligns the heterogeneous domains of different predictors in a shared latent space to facilitate comparisons of predictors independently of the domains on which they are originally defined. We facilitate this by a new data alignment scheme that matches data distributions across task categories. Based on visual attribute ranking experiments on datasets that span diverse task categories (e.g. shoes and animals), we demonstrate that our approach often significantly improves the performances of the initial predictors.
URI
https://scholarworks.unist.ac.kr/handle/201301/53177
URL
https://icml.cc/Conferences/2021/Schedule?showEvent=10420
Appears in Collections:
AI_Conference Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU