Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization

Yan, Junchi; Cho, Minsu; Zha, Hongyuan; Yang, Xiaokang; Chu, Stephen M.

doi:10.1109/tpami.2015.2477832

Cited by 152 publications

(95 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) using data augmentation, which is widely used in deep learning-based image processing. 3) exploring the alignment among two or multiple interaction graphs [31,32] from different species using graph embedding, instead of using only human interaction network. 4) using an end-end learning framework graph convolutional network [33] to directly infer the protein subcellular locations in the proteinprotein network.…”

Section: Discussionmentioning

confidence: 99%

Predicting protein subcellular location using learned distributed representations from a protein-protein network

Pan

Chen

Liu

et al. 2019

Preprint

View full text Add to dashboard Cite

Functions of proteins are in general related to their subcellular locations. To identify the functions of a protein, we first need know where this protein is located. Interacting proteins tend to locate in the same subcellular location. Thus, it is imperative to take the protein-protein interactions into account for computational identification of protein subcellular locations.In this study, we present a deep learning-based method, node2loc, to predict protein subcellular location. node2loc first learns distributed representations of proteins in a protein-protein network using node2vec, which acquires representations from unlabeled data for downstream tasks. Then the learned representations are further fed into a recurrent neural network (RNN) to predict subcellular locations. Considering the severe class imbalance of different subcellular locations, Synthetic Minority Over-sampling Technique (SMOTE) is applied to artificially boost subcellular locations with few proteins.We construct a benchmark dataset with 16 subcellular locations and evaluate node2loc on this dataset. node2loc yields a Matthews correlation coefficient (MCC) value of 0.812, which outperforms other baseline methods. The results demonstrate that the learned presentations from a proteinprotein network have strong discriminate ability for classifying protein subcellular locations and the RNN is a more powerful classifier than traditional machine learning models. node2loc is freely available at https://github.com/xypan1232/node2loc.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting protein subcellular location using learned distributed representations from a protein-protein network

Pan

Chen

Liu

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The main reason is that to the best of our knowledge, there is no specified network designed to solve the problem of face recognition affected by noise as addressed by our model. One possible future work is to involve sparsity based models [54], matching based methods [55], and error-correction based models [56] to further improve cost effectiveness and robustness. The bold indicates the best…”

Section: Discussionmentioning

confidence: 99%

Noise-resistant network: a deep-learning method for face recognition under noise

Ding

Cheng

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

Along with the developments of deep learning, many recent architectures have been proposed for face recognition and even get close to human performance. However, accurately recognizing an identity from seriously noisy face images still remains a challenge. In this paper, we propose a carefully designed deep neural network coined noise-resistant network (NR-Network) for face recognition under noise. We present a multi-input structure in the final fully connected layer of the proposed NR-Network to extract a multi-scale and more discriminative feature from the input image. Experimental results such as the receiver-operating characteristic (ROC) curves on the AR database injected with different noise types show that the NR-Network is visibly superior to some state-of-the-art feature extraction algorithms and also achieves better performance than two deep benchmark networks for face recognition under noise.

show abstract

“…OURS (µ=10), YAN ET AL. [49], and WANG ET AL. [47] consider geometric relations between points, amongst which OURS is the fastest (note that the reported runtimes include the initialisation).…”

Section: Dataset Typementioning

confidence: 93%

“…Practical approaches for solving multi-matching problems can be put into two categories: (i) methods that jointly optimise for multi-matchings between all objects (e.g. [22,49,41,44,6]) and (ii) approaches that first establish matchings between points in each pair of objects independently, and then improve those matchings via a postprocessing procedure referred to as permutation synchronisation [35,12,57,40,30]. Approaches that jointly optimise for multi-matchings either ignore geometric relations between the points [44], or are prohibitively expensive and thus only applicable to small problems (cf.…”

Section: Introductionmentioning

confidence: 99%

HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching

Bernard

Thunberg

Swoboda

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take geometric consistency between points into account. Computationally, the multi-matching problem is difficult. It can be phrased as simultaneously solving multiple (NP-hard) quadratic assignment problems (QAPs) that are coupled via cycle-consistency constraints. The main limitations of existing multi-matching methods are that they either ignore geometric consistency and thus have limited robustness, or they are restricted to small-scale problems due to their (relatively) high computational cost. We address these shortcomings by introducing a Higher-order Projected Power Iteration method, which is (i) efficient and scales to tens of thousands of points, (ii) straightforward to implement, (iii) able to incorporate geometric consistency, (iv) guarantees cycle-consistent multi-matchings, and (iv) comes with theoretical convergence guarantees. Experimentally we show that our approach is superior to existing methods.

show abstract

Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization

Cited by 152 publications

References 45 publications

Predicting protein subcellular location using learned distributed representations from a protein-protein network

Predicting protein subcellular location using learned distributed representations from a protein-protein network

Noise-resistant network: a deep-learning method for face recognition under noise

HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching

Contact Info

Product

Resources

About