【DLゼミ】XFeat: Accelerated Features for Lightweight Image Matchingharmonylab
公開URL:https://arxiv.org/pdf/2404.19174
出典:Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. ascimento: XFeat: Accelerated Features for Lightweight Image Matching, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
概要:リソース効率に優れた特徴点マッチングのための軽量なアーキテクチャ「XFeat(Accelerated Features)」を提案します。手法は、局所的な特徴点の検出、抽出、マッチングのための畳み込みニューラルネットワークの基本的な設計を再検討します。特に、リソースが限られたデバイス向けに迅速かつ堅牢なアルゴリズムが必要とされるため、解像度を可能な限り高く保ちながら、ネットワークのチャネル数を制限します。さらに、スパース下でのマッチングを選択できる設計となっており、ナビゲーションやARなどのアプリケーションに適しています。XFeatは、高速かつ同等以上の精度を実現し、一般的なラップトップのCPU上でリアルタイムで動作します。
セル生産方式におけるロボットの活用には様々な問題があるが,その一つとして 3 体以上の物体の組み立てが挙げられる.一般に,複数物体を同時に組み立てる際は,対象の部品をそれぞれロボットアームまたは治具でそれぞれ独立に保持することで組み立てを遂行すると考えられる.ただし,この方法ではロボットアームや治具を部品数と同じ数だけ必要とし,部品数が多いほどコスト面や設置スペースの関係で無駄が多くなる.この課題に対して音𣷓らは組み立て対象物に働く接触力等の解析により,治具等で固定されていない対象物が組み立て作業中に運動しにくい状態となる条件を求めた.すなわち,環境中の非把持対象物のロバスト性を考慮して,組み立て作業条件を検討している.本研究ではこの方策に基づいて,複数物体の組み立て作業を単腕マニピュレータで実行することを目的とする.このとき,対象物のロバスト性を考慮することで,仮組状態の複数物体を同時に扱う手法を提案する.作業対象としてパイプジョイントの組み立てを挙げ,簡易な道具を用いることで単腕マニピュレータで複数物体を同時に把持できることを示す.さらに,作業成功率の向上のために RGB-D カメラを用いた物体の位置検出に基づくロボット制御及び動作計画を実装する.
This paper discusses assembly operations using a single manipulator and a parallel gripper to simultaneously
grasp multiple objects and hold the group of temporarily assembled objects. Multiple robots and jigs generally operate
assembly tasks by constraining the target objects mechanically or geometrically to prevent them from moving. It is
necessary to analyze the physical interaction between the objects for such constraints to achieve the tasks with a single
gripper. In this paper, we focus on assembling pipe joints as an example and discuss constraining the motion of the
objects. Our demonstration shows that a simple tool can facilitate holding multiple objects with a single gripper.
29. Algorithm: SEAL
SEAL (learning from Subgraphs, Embeddings and Attributes for Link prediction)
- enclosing subgraphを入力にしたgraph classificication
- DGCNN [Zhang+, AAAI’18] をモデル
- 頂点の特徴ベクトル・埋め込みベクトルを扱える
- 問題点
- 辺の両端になる頂点とそうでない頂点を区別する必要
29
http://papers.nips.cc/paper/7763-link-prediction-based-on-graph-neural-networks.pdf
30. Algorithm: SEAL
Node labeling (DRNL)
- 辺の両端 x, y からの距離に応じてラベリング
- 頂点の埋め込みベクトルにDRNLを1-hotにして追加
30
http://papers.nips.cc/paper/7763-link-prediction-based-on-graph-neural-networks.pdf
46. まとめ
46
- 今年のNuerIPSではGNNを扱う論文数が大きく増えた
- 特に molecular generation & computer vision
- Spotlight paper 3本の紹介
- Hierarchical differentiable pooling
- Link prediction based on GNN
- Graph convolutional policy network
- 応用するための基本的な道具は揃いつつある印象
- 何にどう応用するか、が焦点になってきている
47. NeurIPS 2018 でのGNN関連の論文 (1)
- Node classification
- Adaptive Sampling Towards Fast Graph Representation Learning [Huang+]
- Mean-field theory of graph neural networks in graph partitioning [Kawamoto+]
- Graph classification
- Hierarchical Graph Representation Learning with Differentiable Pooling [Ying+]
- Link prediction
- Link Prediction Based on Graph Neural Networks [Zhang+]
- SimplE Embedding for Link Prediction in Knowledge Graphs [Kazemi+]
- Graph generation
- Constrained Generation of Semantically Valid Graphs via Regularizing Variational
Autoencoders [Ma+]
- Constrained Graph Variational Autoencoders for Molecule Design [Liu+]
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
[You+]
47
48. NeurIPS 2018 でのGNN関連の論文 (2)
- Logical / combinatorial task
- Combinatorial Optimization with Graph Convolutional Networks and Guided Tree
Search [Li+]
- Embedding Logical Queries on Knowledge Graphs [Hamilton+]
- Recurrent Relational Networks [Palm+]
- Representation in visual task
- Beyond Grids: Learning Graph Representations for Visual Recognition [Li+]
- Learning Conditioned Graph Structures for Interpretable Visual Question
Answering [Norcliffe-Brown+]
- LinkNet: Relational Embedding for Scene Graph [Woo+]
- Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
[Herzig+]
- Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual
Question Answering [Narasimhan+]
- Symbolic Graph Reasoning Meets Convolutions [Liang+]
48
49. (参考)NIPS 2017 でのGNN関連の論文
- Node classification
- Inductive Representation Learning on Large Graphs [Hamilton+]
- Learning Graph Representations with Embedding Propagation [Duran+]
- Representation in vision
- Pixels to Graphs by Associative Embedding [Newell+]
- Logical / combinatorial task
- Premise Selection for Theorem Proving by Deep Graph Embedding
[Wang+]
- Learning Combinatorial Optimization Algorithms over Graphs [Khalil+]
- Link prediction
- Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
[Monti+]
- Other
- Protein Interface Prediction using Graph Convolutional Networks [Fout+]
49
50. 参考文献
W. Huang, T. Zhang, Y. Rong, and J. Huang, “Adaptive Sampling Towards Fast Graph Representation Learning,” NIPS 2018.
Y. Li and A. Gupta, “Beyond Grids: Learning Graph Representations for Visual Recognition,” NIPS 2018.
Z. Li, Q. Chen, and V. Koltun, “Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search,” NIPS 2018.
T. Ma, J. Chen, and C. Xiao, “Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders,” NIPS 2018.
Q. Liu, M. Allamanis, M. Brockschmidt, and A. Gaunt, “Constrained Graph Variational Autoencoders for Molecule Design,” NIPS 2018.
W. Hamilton, P. Bajaj, M. Zitnik, D. Jurafsky, and J. Leskovec, “Embedding Logical Queries on Knowledge Graphs,” NIPS 2018.
J. You, B. Liu, Z. Ying, V. Pande, and J. Leskovec, “Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation,” NIPS 2018.
M. Simonovsky and N. Komodakis, “GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders,” arXiv:1802.03480 [cs], Feb. 2018.
R. Ying, J. You, C. Morris, X. Ren, W. L. Hamilton, and J. Leskovec, “Hierarchical Graph Representation Learning with Differentiable Pooling,” NIPS 2018.
P. Ertl, R. Lewis, E. Martin, and V. Polyakov, “In silico generation of novel, drug-like chemical matter using the LSTM neural network,” arXiv:1712.07449 [cs, q-bio], Dec.
2017.
W. Norcliffe-Brown, S. Vafeias, and S. Parisot, “Learning Conditioned Graph Structures for Interpretable Visual Question Answering,” NIPS 2018.
A. Garcia Duran and M. Niepert, “Learning Graph Representations with Embedding Propagation,” NIPS 2017.
M. Zhang and Y. Chen, “Link Prediction Based on Graph Neural Networks,” NIPS 2018.
S. Woo, D. Kim, D. Cho, and I. S. Kweon, “LinkNet: Relational Embedding for Scene Graph,” NIPS 2018.
R. Herzig, M. Raboh, G. Chechik, J. Berant, and A. Globerson, “Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction,” NIPS 2018.
M. Olivecrona, T. Blaschke, O. Engkvist, and H. Chen, “Molecular De Novo Design through Deep Reinforcement Learning,” arXiv:1704.07555 [cs], Apr. 2017.
E. J. Bjerrum and R. Threlfall, “Molecular Generation with Recurrent Neural Networks (RNNs),” arXiv:1705.04612 [cs, q-bio], May 2017.
S. Kearnes, K. McCloskey, M. Berndl, V. Pande, and P. Riley, “Molecular Graph Convolutions: Moving Beyond Fingerprints,” Journal of Computer-Aided Molecular Design,
vol. 30, no. 8, pp. 595–608, Aug. 2016.
Y. Li, L. Zhang, and Z. Liu, “Multi-Objective De Novo Drug Design with Conditional Graph Generative Model,” arXiv:1801.07299 [cs, q-bio], Jan. 2018.
A. Grover and J. Leskovec, “node2vec: Scalable Feature Learning for Networks,” KDD 2016.
M. Narasimhan, S. Lazebnik, and A. Schwing, “Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering,” NIPS 2018.
A. Newell and J. Deng, “Pixels to Graphs by Associative Embedding,” NIPS 2017.
M. Wang, Y. Tang, J. Wang, and J. Deng, “Premise Selection for Theorem Proving by Deep Graph Embedding,” NIPS 2017.
A. Fout, J. Byrd, B. Shariat, and A. Ben-Hur, “Protein Interface Prediction using Graph Convolutional Networks,” NIPS 2017.
T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” ICLR 2017.
S. M. Kazemi and D. Poole, “SimplE Embedding for Link Prediction in Knowledge Graphs,” NIPS 2018.
X. Liang, Z. Hu, H. Zhang, L. Lin, and E. P. Xing, “Symbolic Graph Reasoning Meets Convolutions,” NIPS 2018.
S. Abu-El-Haija, B. Perozzi, R. Al-Rfou, and A. A. Alemi, “Watch Your Step: Learning Node Embeddings via Graph Attention,” NIPS 2018.
M. Zhang, Z. Cui, M. Neumann, and Y. Chen, “An End-to-End Deep Learning Architecture for Graph Classification,” AAAI 2018.
F. Monti, M. Bronstein, and X. Bresson, “Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks,” NIPS 2017.
E. Khalil, H. Dai, Y. Zhang, B. Dilkina, and L. Song, “Learning Combinatorial Optimization Algorithms over Graphs,” NIPS 2017.
W. Hamilton, Z. Ying, and J. Leskovec, “Inductive Representation Learning on Large Graphs,” NIPS 2017.
A. Garcia Duran and M. Niepert, “Learning Graph Representations with Embedding Propagation,” NIPS 2017.
50