Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction
Open Access
- 5 January 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Deep learning-based multi-task approaches usually rely on factorizing representation layers up to a certain point, where the network splits into several heads, each one addressing a specific task. Depending on the inter-task correlation, such naive model may or may not allow the tasks to benefit from each others. In this paper, we propose a novel Semantic Orthogonality Spaces (SOS) method for multi-task problems, where each task is predicted using the information from a common subspace that factorizes information among all tasks, as well as a task-specific subspace. We enforce orthogonality between these tasks by applying soft orthogonality constraints, as well as adversarially-learned semantic orthogonality objectives that ensures that predicting one task requires the specific information related to that task. We demonstrate the effectiveness of SOS on synthetic data, as well as for large-scale facial attributes prediction. In particular, we use SOS to craft a lightweight architecture that provides high-end accuracies on CelebA database.Keywords
Funding Information
- ANR (ANR-17-CE33-0002)
This publication has 19 references indexed in Scilit:
- Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification2017
- Improving Facial Attribute Prediction Using Semantic Segmentation2017
- UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory2017
- Multi-Output Random Forests for Facial Action Unit Detection2017
- Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit DetectionInternational Journal of Computer Vision, 2017
- MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes2016
- Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data2016
- Cross-Stitch Networks for Multi-task Learning2016
- Deep Learning Face Attributes in the Wild2015
- Facial Action Unit intensity prediction via Hard Multi-Task Metric Learning for Kernel Regression2015