GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning

Abstract

A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures. Typically, the conventional deep multi-attribute learning approaches follow the pipeline of manually designing the network architectures based on task-specific expertise prior knowledge and careful network tunings, leading to the inflexibility for various complicated scenarios in practice. Motivated by addressing this problem, we propose an efficient greedy neural architecture search approach (GNAS) to automatically discover the optimal tree-like deep architecture for multi-attribute learning. In a greedy manner, GNAS divides the optimization of global architecture into the optimizations of individual connections step by step. By iteratively updating the local architectures, the global tree-like architecture gets converged where the bottom layers are shared across relevant attributes and the branches in top layers more encode attribute-specific features. Experiments on three benchmark multi-attribute datasets show the effectiveness and compactness of neural architectures derived by GNAS, and also demonstrate the efficiency of GNAS in searching neural architectures.

arXiv commentACM MM 2018 (Oral)

References in corpus (6)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Neural Architecture Search with Reinforcement Learning
• How transferable are features in deep neural networks?
• Improving Person Re-identification by Attribute and Identity Learning
• Efficient Neural Architecture Search via Parameter Sharing
• Neural Architecture Search with Bayesian Optimisation and Optimal Transport

Cited by in corpus (3)

• GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
• Branched Multi-Task Networks: Deciding What Layers To Share
• STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map