cvpaper.challenge2019のMeta Study Groupでの発表スライド
点群深層学習についてのサーベイ ( https://www.slideshare.net/naoyachiba18/ss-120302579 )を経た上でのMeta Study
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
cvpaper.challenge2019のMeta Study Groupでの発表スライド
点群深層学習についてのサーベイ ( https://www.slideshare.net/naoyachiba18/ss-120302579 )を経た上でのMeta Study
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
2018/10/20コンピュータビジョン勉強会@関東「ECCV読み会2018」発表資料
Yew, Z. J., & Lee, G. H. (2018). 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration. European Conference on Computer Vision.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This document summarizes a paper titled "DeepI2P: Image-to-Point Cloud Registration via Deep Classification". The paper proposes a method for estimating the camera pose within a point cloud map using a deep learning model. The model first classifies whether points in the point cloud fall within the camera's frustum or image grid. It then performs pose optimization to estimate the camera pose by minimizing the projection error of inlier points onto the image. The method achieves more accurate camera pose estimation compared to existing techniques based on feature matching or depth estimation. It provides a new approach for camera localization using point cloud maps without requiring cross-modal feature learning.
2020/10/10に開催された第4回全日本コンピュータビジョン勉強会「人に関する認識・理解論文読み会」発表資料です。
以下の2本を読みました
Harmonious Attention Network for Person Re-identification. (CVPR2018)
Weekly Supervised Person Re-Identification (CVPR2019)
5. PointNet
5
Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). PointNet : Deep
Learning on Point Sets for 3D Classification and Segmentation
Big Data + Deep Representation Learning. IEEE Conference on
ComputerVision and Pattern Recognition (CVPR).
各点群の点を独立に畳み込む
Global Max Poolingで点群全体の特徴量を取得
各点を個別
に畳み込み
アフィン変換
各点の特徴を統合
6. PointNet++
6
Qi, C. R.,Yi, L., Su, H., & Guibas, L. J. (2017). PointNet++: Deep
Hierarchical Feature Learning on Point Sets in a Metric Space.
Conference on Neural Information Processing Systems (NIPS).
PointNetを階層的に適用
点群をクラスタ分割→PointNet→クラスタ内で統合を繰り返す
14. CVPR2018で紹介された点群畳み込み研究
14
1. Hua, B.-S.,Tran, M.-K., &Yeung, S.-K.“Pointwise Convolutional Neural
Networks”
2. Le,T., & Duan,Y. “PointGrid:A Deep Network for 3D Shape
Understanding”
3. Huang, Q.,Wang,W., & Neumann,“U. Recurrent Slice Networks for 3D
Segmentation of Point Clouds”
4. Li, J., Chen, B. M., & Lee, G. H.“SO-Net: Self-Organizing Network for
Point Cloud Analysis”
5. Shen,Y., Feng, C.,Yang,Y., &Tian, D.“Mining Point Cloud Local Structures
by Kernel Correlation and Graph Pooling”
6. Liu, S., Xie, S., Chen, Z., &Tu, Z.“Attentional ShapeContextNet for Point
Cloud Recognition”
7. Tatarchenko, M., Park, J., Koltun,V., & Zhou, Q. “Tangent convolutions for
dense prediction in 3D”
8. Wang, S., Suo, S., Ma,W., & Urtasun, R. “Deep Parametric Continuous
Convolutional Neural Networks”
9. Su, H., Jampani,V., Sun, D., Maji, S., Kalogerakis, E.,Yang, M.-H., & Kautz, J.
“SPLATNet: Sparse Lattice Networks for Point Cloud Processing”