Back to Search
Start Over
Universal Representations: A Unified Look at Multiple Task and Domain Learning.
- Source :
-
International Journal of Computer Vision . May2024, Vol. 132 Issue 5, p1521-1545. 25p. - Publication Year :
- 2024
-
Abstract
- We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple loss functions with different magnitudes and characteristics and thus results in unbalanced state of one loss dominating the optimization and poor results compared to learning a separate model for each problem. To this end, we propose distilling knowledge of multiple task/domain-specific networks into a single deep neural network after aligning its representations with the task/domain-specific ones through small capacity adapters. We rigorously show that universal representations achieve state-of-the-art performances in learning of multiple dense prediction problems in NYU-v2 and Cityscapes, multiple image classification problems from diverse domains in Visual Decathlon Dataset and cross-domain few-shot learning in MetaDataset. Finally we also conduct multiple analysis through ablation and qualitative studies. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*IMAGE recognition (Computer vision)
Subjects
Details
- Language :
- English
- ISSN :
- 09205691
- Volume :
- 132
- Issue :
- 5
- Database :
- Academic Search Index
- Journal :
- International Journal of Computer Vision
- Publication Type :
- Academic Journal
- Accession number :
- 177079209
- Full Text :
- https://doi.org/10.1007/s11263-023-01931-6