Can I read MonoLSS: Learnable Sample Selection For Monocular 3D Detection on EtoBox?

MonoLSS: Learnable Sample Selection For Monocular 3D Detection by Li, Zhenjia; Jia, Jinrang; Shi, Yifeng is a scholarly article available to read on EtoBox.

What is MonoLSS: Learnable Sample Selection For Monocular 3D Detection about?

In the field of autonomous driving, monocular 3D detection is a critical task which estimates 3D properties (depth, dimension, and orientation) of objects in a single RGB image. Previous works have used features in a heuristic way to learn 3D properties, without considering that inappropriate features could have adverse effects. In this paper, sample selection is introduced that only suitable samples should be trained to regress the 3D properties. To select samples adaptively, we propose a Learnable Sample Selection (LSS) module, which is based on Gumbel-Softmax and a relative-distance sample divider. The LSS module works under a warm-up strategy leading to an improvement in training stability. Additionally, since the LSS module dedicated to 3D property sample selection relies on object-level features, we further develop a data augmentation method named MixUp3D to enrich 3D property samples which conforms to imaging principles without introducing ambiguity. As two orthogonal methods, the LSS module and MixUp3D can be utilized independently or in conjunction. Sufficient experiments have shown that their combined use can lead to synergistic effects, yielding improvements that transce

Author

Li, Zhenjia; Jia, Jinrang; Shi, Yifeng

Published

2023

Language

EN