PointNetおさらい：出典 18 PointNet 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 Computer Vision and Pattern Recognition (CVPR). PointNet++ 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 (NeurIPS) PointNeXt Qian, G., Li, Y., Peng, H., Mai, J., Hammoud, H. A. A. K., Elhoseiny, M., & Ghanem, B. (2022). PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies. Conference on Neural Information Processing Systems (NeurIPS).
Transformerおさらい: 出典 38 Transformer Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS). Vision Transformer Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image Is Worth 16x16 Words: Transformers For Image Recognition At Scale. International Conference on Learning Representations (ICLR).
Transformerおさらい: 出典 39 MLP Mixer Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., Lucic, M., & Dosovitskiy, A. (2021). MLP-Mixer: An all-MLP Architecture for Vision. Advances in Neural Information Processing Systems Meta Former (Pool Former) Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., & Yan, S. (2022). MetaFormer is Actually What You Need for Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Point Transformer V2 64 Wu, X., Lao, Y., Jiang, L., Liu, X., & Zhao, H. (2022). Point Transformer V2: Grouped Vector Attention and Partition- based Pooling. Advances in Neural Information Processing Systems (NeurIPS), NeurIPS Point Transformerに対して、以下を導入することで性能改善 Grouped Vector Attention より強力なPositional Embedding Partition Based Pooling
PointMixer 70 Choe, J., Park, C., Rameau, F., Park, J., & Kweon, I. S. (2022). PointMixer: MLP-Mixer for Point Cloud Understanding. European Conference on Computer Vision (ECCV) MLP Mixerを、点群のような疎で乱雑なデータに対して適用す るために、Token-Mixing部分をChannel-MixingとSoftmaxの組 み合わせで置き換え Inter-Set、Intra-Set、Hierarchical-Setの３パターンでmixing 高効率
PCT: Point Cloud Transformer 89 Guo, M. H., Cai, J. X., Liu, Z. N., Mu, T. J., Martin, R. R., & Hu, S. M. (2021). PCT: Point cloud transformer. Computational Visual Media, 7(2), 187–199. 点群の座標を特徴量へ変換し、通常のTransformerと同様、 Key、Queryの内積を用いてＡｔｔｅｎｔｉｏｎを生成し、Valueに重み づけ 全ての点同士でSelf-Attentionを計算 グラフ理論で用いられるラプラシアン行列を用いたOffset Attentionを導入することで、順序不変なAttentionを実装
Fast Point Transformer 112 Park, C., Jeong, Y., Cho, M., & Park, J. (2022). Fast Point Transformer. Conference on Computer Vision and Pattern Recognition (CVPR) Light Weightな局所領域でのSelf-Attention Blockを導入 Voxel-Hashingベースアーキテクチャによって、Point Transformerと比較して129倍の推論の高速化
Self-Positioning Point-based Transformer (SPoTr) 153 Park, J., Lee, S., Kim, S., Xiong, Y., & Kim, H. J. (2023). Self-positioning Point-based Transformer for Point Cloud Understanding. Conference on Computer Vision and Pattern Recognition (CVPR). リソース削減のために、全ての点同士のSelf- Attentionを取るのではなく、グローバルおよびロー カルの特徴を捉えたself-positioning point (SP point) を使用。 SP pointを用いてローカルおよびグローバルなCross- Attentionを取ることで、3つのベンチマーク(SONN, SN-Part, and S3DIS)でSOTA達成
takmin
isaoshimizu
moritamasami
hcrane
niryuu
caori_t
bcantrill
charmichokshi
newrelic2023
bun913
sat
kawaguti
bitkey
colly
sachag
geoffreycrofte
jrom
chriscoyier
brianwarren
addyosmani
caitiem20
tmm1
stephaniewalter
mraible