Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification

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 subject to designer's bias, which can be both error-prone and tedious. In this work, we propose a principled approach for designing compact multi-task deep learning architectures. Our approach starts with a thin network and dynamically widens it in a greedy manner during training using a novel criterion that promotes grouping of similar tasks together. Our Extensive 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.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Theoretical Models of Learning to Learn
• Learning Deep Representation for Face Alignment with Auxiliary Attributes
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• An exploration of parameter redundancy in deep networks with circulant projections

Cited by in corpus (4)

• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
• Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction
• Tackling Ordinal Regression Problem for Heterogeneous Data: Sparse and Deep Multi-Task Learning Approaches