A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
We show that we can maximize the mutual information between 3D objects and their "chunks" to improve the representations in aligned datasets. ...
To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. ...
of a 3D object for mutual information maximization. ...
arXiv:2006.02598v2
fatcat:btxte6op5rhvrmqlqvi2lf2lle
Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Experimental evaluations on downstream applications such as 3D object classification and semantic segmentation demonstrate the effectiveness of our framework and show that it can outperform state-of-the-art ...
For another, we provide an instance-level contrasting method to learn the global geometry, which is formulated by maximizing the similarity between two augmentations of one point cloud. ...
For example, in order to learn representations, Info3D [22] maximizes the mutual information between the 3D shape and a geometric transformed version of the 3D shape. ...
arXiv:2202.02543v2
fatcat:4khokaqzrfgqndxz2hj3gnvw6a
Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
point cloud as positive samples and otherwise negative ones to facilitate the task of contrastive learning. ...
Point clouds have attracted increasing attention as a natural representation of 3D shapes. ...
Recently, Info3D [57] proposed to extend the InfoMax and contrastive learning framework on 3D objects, which maximizes the mutual information between 3D objects and their "chunks" to learn representations ...
arXiv:2107.01886v1
fatcat:apwif67eijf4jljcoaqboomlve
3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data. ...
Then we design a dual-branch contrastive network with an encoder for each branch and a subsequent common projection head. ...
It maximized the mutual information between 3D objects and their "chunks" to improve the representation in the aligned dataset. ...
arXiv:2201.02198v2
fatcat:p2tykgne3vaqdnuvzfbvmdeyni