Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

Tang, Lulu; Chen, Ke; Wu, Chaozheng; Yu, Haiyang; Jia, Kui; Yang, Zhi-Xin

doi:10.48550/arxiv.2001.04803

Cited by 4 publications

(3 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [11] introduced half-to-half point cloud prediction self-supervised task in a multi-angle scenario, where RNN was explored to predict the back half point cloud based on the front half. In [29], a novel geometric self-supervised learning task was proposed to predict point cloud local geometric information like normal and curvature. The second strategy is to first destroy a point cloud and then train a neural network to reconstruct it.…”

Section: Self-supervised Learning On Point Cloudsmentioning

confidence: 99%

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Luo,

Liu,

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep neural networks have achieved promising performance in supervised point cloud applications, but manual annotation is extremely expensive and time-consuming in supervised learning schemes. Unsupervised domain adaptation (UDA) addresses this problem by training a model with only labeled data in the source domain but making the model generalize well in the target domain. Existing studies show that self-supervised learning using both source and target domain data can help improve the adaptability of trained models, but they all rely on hand-crafted designs of the self-supervised tasks. In this paper, we propose a learnable self-supervised task and integrate it into a selfsupervision-based point cloud UDA architecture. Specifically, we propose a learnable nonlinear transformation that transforms a part of a point cloud to generate abundant and complicated point clouds while retaining the original semantic information, and the proposed self-supervised task is to reconstruct the original point cloud from the transformed ones. In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation, so that the encoder can be trained to extract features suitable for both the source and the target domain data. Experiments on PointDA-10 and PointSegDA datasets show that the proposed method achieves new state-of-the-art performance on both classification and segmentation tasks of point cloud UDA. Code will be made publicly available.

show abstract

Section: Self-supervised Learning On Point Cloudsmentioning

confidence: 99%

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Luo,

Liu,

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…[4] learns a point-cloud auto-encoder that also predicts pairwise relations between the points. [40] suggested learning local geometric properties by training a network to predict the point normal vector and curvature.…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Learning for Domain Adaptation on Point-Clouds

Achituve¹,

Maron²,

Chechik³

2020

Preprint

View full text Add to dashboard Cite

Self-supervised learning (SSL) allows to learn useful representations from unlabeled data and has been applied effectively for domain adaptation (DA) on images. It is still unknown if and how it can be leveraged for domain adaptation for 3D perception. Here we describe the first study of SSL for DA on point-clouds. We introduce a new pretext task, Region Reconstruction, motivated by the deformations encountered in sim-to-real transformation. We also demonstrate how it can be combined with a training procedure motivated by the MixUp method. Evaluations on six domain adaptations across synthetic and real furniture data, demonstrate large improvement over previous work.

show abstract

“…In many other domains, it is not even clear which auxiliary tasks could be beneficial. For example, for point cloud classification, few self-supervised tasks have been proposed, and their benefits are limited so far [1,19,40,45]. This is also the case for learning in domains outside perception, where more specialized expert knowledge may be needed for designing useful auxiliary tasks.…”

Section: Introductionmentioning

confidence: 99%

Auxiliary Learning by Implicit Differentiation

Navon¹,

Achituve²,

Maron³

et al. 2020

Preprint

View full text Add to dashboard Cite

Training with multiple auxiliary tasks is a common practice used in deep learning for improving the performance on the main task of interest. Two main challenges arise in this multi-task learning setting: (i) Designing useful auxiliary tasks; and (ii) Combining auxiliary tasks into a single coherent loss. We propose a novel framework, AuxiLearn, that targets both challenges, based on implicit differentiation. First, when useful auxiliaries are known, we propose learning a network that combines all losses into a single coherent objective function. This network can learn non-linear interactions between auxiliary tasks. Second, when no useful auxiliary task is known, we describe how to learn a network that generates a meaningful, novel auxiliary task. We evaluate AuxiLearn in a series of tasks and domains, including image segmentation and learning with attributes. We find that AuxiLearn consistently improves accuracy compared with competing methods.

show abstract

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

Cited by 4 publications

References 55 publications

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Self-Supervised Learning for Domain Adaptation on Point-Clouds

Auxiliary Learning by Implicit Differentiation

Contact Info

Product

Resources

About