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
データ拡張 (Data Augmentation) を学習中に使い分けるRefined Data Augmentationについて解説しました。
He, Zhuoxun, et al. "Data augmentation revisited: Rethinking the distribution gap between clean and augmented data." arXiv preprint arXiv:1909.09148 (2019).
データ拡張 (Data Augmentation) を学習中に使い分けるRefined Data Augmentationについて解説しました。
He, Zhuoxun, et al. "Data augmentation revisited: Rethinking the distribution gap between clean and augmented data." arXiv preprint arXiv:1909.09148 (2019).
YouTube nnabla channelの次の動画で利用したスライドです。
【DeepLearning研修】Transformerの基礎と応用 --第3回 Transformerの画像での応用
https://youtu.be/rkuayDInyF0
【参考文献】
・Deep Residual Learning for Image Recognition
https://arxiv.org/abs/1512.03385
・An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
https://arxiv.org/abs/2010.11929
・ON THE RELATIONSHIP BETWEEN SELF-ATTENTION AND CONVOLUTIONAL LAYERS
https://arxiv.org/abs/1911.03584
・Image Style Transfer Using Convolutional Neural Networks
https://ieeexplore.ieee.org/document/7780634
・Are Convolutional Neural Networks or Transformers more like human vision
https://arxiv.org/abs/2105.07197
・HOW DO VISION TRANSFORMERS WORK?
https://arxiv.org/abs/2202.06709
・Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://arxiv.org/abs/1610.02391
・Quantifying Attention Flow in Transformers
https://arxiv.org/abs/2005.00928
・Transformer Interpretability Beyond Attention Visualization
https://arxiv.org/abs/2012.09838
・End-to-End Object Detection with Transformers
https://arxiv.org/abs/2005.12872
・SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
https://arxiv.org/abs/2105.15203
・Training data-efficient image transformers & distillation through attention
https://arxiv.org/abs/2012.12877
・Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://arxiv.org/abs/2103.14030
・Masked Autoencoders Are Scalable Vision Learners
https://arxiv.org/abs/2111.06377
・Emerging Properties in Self-Supervised Vision Transformers
https://arxiv.org/abs/2104.14294
・Scaling Laws for Neural Language Models
https://arxiv.org/abs/2001.08361
・Learning Transferable Visual Models From Natural Language Supervision
https://arxiv.org/abs/2103.00020
・Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
https://arxiv.org/abs/2403.03206
・Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
https://arxiv.org/abs/2402.17177
・SSII2024技術マップ
https://confit.atlas.jp/guide/event/ssii2024/static/special_project_tech_map
文献紹介:TSM: Temporal Shift Module for Efficient Video UnderstandingToru Tamaki
Ji Lin, Chuang Gan, Song Han; TSM: Temporal Shift Module for Efficient Video Understanding, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 7083-7093
https://openaccess.thecvf.com/content_ICCV_2019/html/Lin_TSM_Temporal_Shift_Module_for_Efficient_Video_Understanding_ICCV_2019_paper.html
21. 論文の紹介
21
• STN
– Spatial Transformer Networks
M. Jaderberg+ / NIPS2015 (arXiv:1506.02025)
• PointNet
– PointNet: Deep Learning on Point Sets for 3D
Classification and Segmentation
C. R. Qi+ / CVPR2017 (arXiv:1612.00593)
スライドのフォーマットが
サーベイスライドのままなのはお許し下さい..
46. 46
• PointNetが本当にブレイクスルーだったのか
PointNetのちょっと前にSymmetric Functionで
点群を扱う論文が出ている
• Deep Learning with Sets and Point Clouds
– S. Ravanbakhsh, J. Schneider, B. Poczos. / ICLR2017-WS
– 2016/11/14 (arxiv:1611.04500)
• PointNet
– C. R. Qi, H. Su, K. Mo, L. J. Guibas. / CVPR2017
– 2016/12/02 (arxiv:1612.00593)
• Deep Sets
– M. Zaheer, S. Kottur, S. Ravanbakhsh, B. Poczos, R. Salakhutdinov,
A. Smola. / NIPS2017
– 2017/03/10 (arXiv:1703.06114)
有名になる要因はアイデアの新しさだけではない
考えられる他の要因例:
学会,完成度,評価,見せ方,タイトル,初期の被引用数・・・
メタな話