Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
Authors:
- Yongxi LuYLYongxi Lu
- Abhishek KumarAKAbhishek Kumar
- Shuangfei ZhaiSZShuangfei Zhai
- Yu ChengYCYu Cheng
- Tara JavidiTJTara Javidi
- Rogerio FerisRFRogerio Feris
Top Cited Papers
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1131-1140
Abstract
Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed network architectures with layers that are shared across tasks and branches that encode task-specific features. However, the space of possible multi-task deep architectures is combinatorially large and often the final architecture is arrived at by manual exploration of this space, which can be both error-prone and tedious. We propose an automatic approach for designing compact multi-task deep learning architectures. Our approach starts with a thin multi-layer network and dynamically widens it in a greedy manner during training. By doing so iteratively, it creates a tree-like deep architecture, on which similar tasks reside in the same branch until at the top layers. Evaluation on person attributes classification tasks involving facial and clothing attributes suggests that the models produced by the proposed method are fast, compact and can closely match or exceed the state-of-the-art accuracy from strong baselines by much more expensive models.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Deep Expectation of Real and Apparent Age from a Single Image Without Facial LandmarksInternational Journal of Computer Vision, 2016
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations2016
- Cross-Stitch Networks for Multi-task Learning2016
- Deep Learning Face Attributes in the Wild2015
- Person Attribute Recognition with a Jointly-Trained Holistic CNN Model2015
- Channel-level acceleration of deep face representationsIEEE Access, 2015
- Going deeper with convolutions2015
- “Wow! You Are So Beautiful Today!”ACM Transactions on Multimedia Computing, Communications, and Applications, 2014
- Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets2013
- Learning to Learn1998