paper-with-me

Papers

Learning to Sample

2018-12-04 · CVPR 2019 6 · Oren Dovrat, Itai Lang, Shai Avidan

Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS). However, FPS is agnostic to a downstream application (classification, retrieval, etc.). The underlying assumption seems to be that minimizing the farthest point distance, as done by FPS, is a good proxy to other objective functions. We show that it is better to learn how to sample. To do that, we propose a deep network to simplify 3D point clouds. The network, termed S-NET, takes a point cloud and produces a smaller point cloud that is optimized for a particular task. The simplified point cloud is not guaranteed to be a subset of the original point cloud. Therefore, we match it to a subset of the original points in a post-processing step. We contrast our approach with FPS by experimenting on two standard data sets and show significantly better results for a variety of applications. Our code is publicly available at: https://github.com/orendv/learning_to_sample

📄 PDF Abstract BibTeX arXiv:1812.01659

Code (1)

orendv/learning_to_sample 공식 구현 tf

Tasks

3D Point Cloud Classification3D Point Cloud ReconstructionRetrieval

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples

2023-11-01 · Hengkui Dong, Xianzhong Long, Yun Li

Contrastive learning predicts whether two images belong to the same category by training a model to make their feature representations as close or as far away as possible. In this paper, we rethink how to mine samples in…

Contrastive LearningData Augmentation

Reliable Imputed-Sample Assisted Vertical Federated Learning

2025-01-11 · Yaopei Zeng, Lei Liu, Shaoguo Liu, Hongjian Dou 외

Vertical Federated Learning (VFL) is a well-known FL variant that enables multiple parties to collaboratively train a model without sharing their raw data. Existing VFL approaches focus on overlapping samples among diffe…

Federated LearningMissing ValuesVertical Federated Learning

A Sample Complexity Measure with Applications to Learning Optimal Auctions

2017-04-09 · NeurIPS 2017 12 · Vasilis Syrgkanis

We introduce a new sample complexity measure, which we refer to as split-sample growth rate. For any hypothesis $H$ and for any sample $S$ of size $m$, the split-sample growth rate $\hat{\tau}_H(m)$ counts how many diffe…

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

2023-09-07 · ICCV 2023 1 · Guan Gui, Zhen Zhao, Lei Qi, Luping Zhou 외

In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classifie…

Test Sample Accuracy Scales with Training Sample Density in Neural Networks

2021-06-15 · Xu Ji, Razvan Pascanu, Devon Hjelm, Balaji Lakshminarayanan 외

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples are surrounded by seen training samples in representation space. We find that a bo…

image-classificationImage ClassificationPrediction