Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

Yang, Bo; Wang, Sen; Markham, Andrew; Trigoni, Niki

doi:10.1007/s11263-019-01217-w

Cited by 118 publications

(75 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, we turn to the powerful attention mechanism to automatically learn important local features. In particular, inspired by [69], our attentive pooling unit consists of the following steps. Computing Attention Scores.…”

Section: Local Feature Aggregationmentioning

confidence: 99%

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

100

View full text Add to dashboard Cite

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200× faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

show abstract

Section: Local Feature Aggregationmentioning

confidence: 99%

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

100

View full text Add to dashboard Cite

show abstract

“…Ilse et al (2018) proposed to use attention-based weighted sum-pooling for multiple instance learning. Similarly, Yang et al (2020) proposed an attentionbased algorithm to aggregate a deep feature set for multi-view 3D reconstruction.…”

Section: Related Workmentioning

confidence: 99%

Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study

Tao¹,

Gao²,

Li³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Sequential information, a.k.a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders. However, is it possible to encode natural languages without orders? Given a bag of words from a disordered sentence, humans may still be able to understand what those words mean by reordering or reconstructing them. Inspired by such an intuition, in this paper, we perform a study to investigate how "order" information takes effects in natural language learning. By running comprehensive comparisons, we quantitatively compare the ability of several representative neural models to organize sentences from a bag of words under three typical scenarios, and summarize some empirical findings and challenges, which can shed light on future research on this line of work.

show abstract

“…Particularly the ModelNet40 dataset (Wu et al, 2015) has been used to test four of the mentioned models. Whilst AttSets (Yang et al, 2020) employs it to formulate a multi-view reconstruction task, the other three methods are tested on the core classification task with PointNet reaching an accuracy of 0.892 (Qi et al, 2017), DeepSets 0.900 (Zaheer et al, 2017) and the Set Transformer 0.904 (Lee et al, 2019). However, the specific methods used to produce the point clouds from the provided mesh representation of objects showcased certain differences, further highlighting the need for a systematic, uniform comparison.…”

Section: Notes On Dataset Performancementioning

confidence: 99%

Set-to-Sequence Methods in Machine Learning: A Review

Jurewicz¹,

Derczynski

2021

jair

View full text Add to dashboard Cite

Machine learning on sets towards sequential output is an important and ubiquitous task, with applications ranging from language modelling and meta-learning to multi-agent strategy games and power grid optimization. Combining elements of representation learning and structured prediction, its two primary challenges include obtaining a meaningful, permutation invariant set representation and subsequently utilizing this representation to output a complex target permutation. This paper provides a comprehensive introduction to the _eld as well as an overview of important machine learning methods tackling both of these key challenges, with a detailed qualitative comparison of selected model architectures.

show abstract

Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

Cited by 118 publications

References 40 publications

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study

Set-to-Sequence Methods in Machine Learning: A Review

Contact Info

Product

Resources

About