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

04/19/2018
by   Siyu Huang, et al.
1

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.

READ FULL TEXT
research
09/24/2020

Disentangled Neural Architecture Search

Neural architecture search has shown its great potential in various area...
research
11/16/2016

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

Multi-task learning aims to improve generalization performance of multip...
research
10/06/2022

POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique

Automating the research for the best neural network model is a task that...
research
08/24/2020

Automated Search for Resource-Efficient Branched Multi-Task Networks

The multi-modal nature of many vision problems calls for neural network ...
research
04/25/2019

TreeGrad: Transferring Tree Ensembles to Neural Networks

Gradient Boosting Decision Tree (GBDT) are popular machine learning algo...
research
07/16/2023

Neural Architecture Retrieval

With the increasing number of new neural architecture designs and substa...
research
05/26/2023

FSD: Fully-Specialized Detector via Neural Architecture Search

In this paper, we first propose and examine a fully-automatic pipeline t...

Please sign up or login with your details

Forgot password? Click here to reset