Proceedings ArticleDOI
Deep Graphical Feature Learning for the Feature Matching Problem
Zhen Zhang,Wee Sun Lee +1 more
- pp 5087-5096
TLDR
This paper proposes a graph neural network model to transform coordinates of feature points into local features and shows promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed method.Abstract:
The feature matching problem is a fundamental problem in various areas of computer vision including image registration, tracking and motion analysis. Rich local representation is a key part of efficient feature matching methods. However, when the local features are limited to the coordinate of key points, it becomes challenging to extract rich local representations. Traditional approaches use pairwise or higher order handcrafted geometric features to get robust matching; this requires solving NP-hard assignment problems. In this paper, we address this problem by proposing a graph neural network model to transform coordinates of feature points into local features. With our local features, the traditional NP-hard assignment problems are replaced with a simple assignment problem which can be solved efficiently. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed method.read more
Citations
More filters
Proceedings Article
Deep Graph Matching Consensus
TL;DR: This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs that scales well to large, real-world inputs while still being able to recover global correspondences consistently.
Posted Content
Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching
TL;DR: This paper presents a QAP network directly learning with the affinity matrix (equivalently the association graph) whereby the matching problem is translated into a vertex classification task, and is the first network to directly learn with the general Lawlers QAP.
Posted Content
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
TL;DR: This work proposes an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers and highlights the conceptual advantages of incorporating solvers into deep learning architectures.
Posted Content
Deep Graph Matching Consensus
TL;DR: Deep Graph Matching Consensus (DGC) as discussed by the authors is a two-stage neural architecture for learning and refining structural correspondences between graphs, which uses localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondence between nodes.
Book ChapterDOI
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers.
TL;DR: In this paper, an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers is proposed, which is the state-of-the-art on keypoint correspondence benchmarks.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Related Papers (5)
A spectral technique for correspondence problems using pairwise constraints
Marius Leordeanu,Martial Hebert +1 more
Poselets: Body part detectors trained using 3D human pose annotations
Lubomir Bourdev,Jitendra Malik +1 more