Auto-MVCNN: Neural Architecture Search for Multi-view 3D Shape Recognition

TL;DR

Auto-MVCNN introduces an automated neural architecture search tailored for multi-view 3D shape recognition, outperforming manual designs and achieving state-of-the-art results by optimizing view feature fusion.

Contribution

The paper presents a novel gradient-based neural architecture search method specifically designed for multi-view 3D shape recognition, including automatic fusion cell optimization.

Findings

Searched architectures outperform manual counterparts

Achieves state-of-the-art performance in 3D shape recognition

Effective end-to-end scheme enhances retrieval accuracy

Abstract

In 3D shape recognition, multi-view based methods leverage human's perspective to analyze 3D shapes and have achieved significant outcomes. Most existing research works in deep learning adopt handcrafted networks as backbones due to their high capacity of feature extraction, and also benefit from ImageNet pretraining. However, whether these network architectures are suitable for 3D analysis or not remains unclear. In this paper, we propose a neural architecture search method named Auto-MVCNN which is particularly designed for optimizing architecture in multi-view 3D shape recognition. Auto-MVCNN extends gradient-based frameworks to process multi-view images, by automatically searching the fusion cell to explore intrinsic correlation among view features. Moreover, we develop an end-to-end scheme to enhance retrieval performance through the trade-off parameter search. Extensive experimental results show that the searched architectures significantly outperform manually designed counterparts in various aspects, and our method achieves state-of-the-art performance at the same time.