Abstract
Numerous deep learning applications benefit from multitask learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.
Keywords
HomoscedasticityComputer scienceArtificial intelligenceTask (project management)WeightingMulti-task learningRegressionMachine learningSemantics (computer science)Deep learningProcess (computing)MonocularPattern recognition (psychology)MathematicsStatisticsHeteroscedasticity
Affiliated Institutions
Related Publications
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different en...
Deep Ordinal Regression Network for Monocular Depth Estimation
Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by explori...
Pedestrian detection aided by deep learning semantic tasks
Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn discriminative features from raw pixels. However, they treat pedestria...
Learning Deep Architectures for AI
Can machine learning deliver AI? Theoretical results, inspiration from the brain and cognition, as well as machine learning experiments suggest that in order to learn the kind o...
Learning Transferable Features with Deep Adaptation Networks
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually...
Publication Info
- Year
- 2018
- Type
- article
- Pages
- 7482-7491
- Citations
- 2556
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
2556
OpenAlex
344
Influential
1136
CrossRef
Cite This
Roberto Cipolla,
Yarin Gal,
Alex Kendall
(2018).
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
, 7482-7491.
https://doi.org/10.1109/cvpr.2018.00781
Identifiers
- DOI
- 10.1109/cvpr.2018.00781
- arXiv
- 1705.07115