Robotics and Computer Vision Lab

Publications

조회 수 45 댓글 0
Extra Form
저 자 Tae-Hyun Oh
학 회 KAIST
논문일시(Year) 2017
논문일시(Month) 5

제목: 사전 정보를 이용한 강인한 행렬 계수 최적화 

 

Committee: 

In So Kweon (Dept. of EE)

Jinwoo Shin (Dept. of EE)

Jong Chul Ye (Dept. of Bio and Brain Engineering, Dept. Mathematical Sciences)

Junmo Kim (Dept. of EE)

Yasuyuki Matsushita (Osaka University)

 

Abstract:

Low-rank matrix recovery arises from many engineering and applied science problems. Rank minimization is a crucial regularizer to derive a low-rank solution, which has attracted much attention. Since directly solving rank minimization is an NP-hard problem, its tightest convex surrogate has been solved instead. In literature, while the convex relaxation has proven that under some mild conditions, exact recoverability is guaranteed, i.e., the global optimal solution of the approximate problem matches the global optimal one of the original NP-hard problem, many real-world problems do not often satisfy these conditions. Furthermore, in this case, the optimal solution of the convex surrogate is departing from the true solution.

This is a problem caused by the approximation gap. Although many non-convex approaches have been proposed to reduce the gap, there has been no remarkable improvement. In this regard, I focus on the fact that the approaches have not exploited prior information according to the data generation procedure of each problem. In this dissertation, I leverage prior information, which naturally arises from each problem definition itself, so that performance degradation caused by the gap can be improved. The contributions of this dissertation are as follows.

(1) By proposing a soft rank constraint, the rank of a low-rank solution is encouraged to be close to the target rank. By virtue of this simple additional information, it properly deals with a deficient number of data regimes where the convex nuclear norm approach fails.

(2) I propose a method to learn priors from data in the empirical Bayesian manner. This method demonstrates the state-of-the-art performance. Surprisingly, the proposed method outperforms the matrix completion method, which assumes the perfect knowledge of exact outlier locations, without such prior knowledge.

(3) I extend the learning prior approach such that the prior information of rank and fractional outlier location is leveraged, i.e., robust matrix completion with rank prior. This further improves the success regimes of the algorithm.

The proposed methods are applied to the various real computer vision problems to demonstrate their practicality (in terms of quality and efficiency). The above three contributions have shown the fundamental performance improvement. This implies that the applicability range has widened far beyond at least the vast range of applications of the existing problems, e.g., PCA and matrix completion. Namely, the practicality of the low-rank approach has improved dramatically.


List of Articles
» Robust Low-rank Optimization with Priors
Tae-Hyun Oh
KAIST 2017 / 5
550. EPINET: A Fully-Convolutional Neural Network using Epipolar Geometry for Depth from Light Field Images
Changha Shin, Hae-Gon Jeon, Youngjin Yoon, In So Kweon, Seon Joo Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 / 06
549. Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
Jongchan Park, Joon-Young Lee, Donggeun Yoo, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 / 06
548. Robust Depth Estimation from Auto Bracketed Images
Sunghoon Im, Hae-Gon Jeon, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 / 06
547. Learning to Localize Sound Source in Visual Scenes
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 2018 / 06
546. Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation
Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 / 06
545. Real-Time Head Pose Estimation using Multi-Task Deep Neural Network
Byungtae Ahn, Dong-Geol Choi, Jaesik Park, In So Kweon
Robotics and Autonomous Systems 2018 / 05
544. Depth from a Light Field Image with Learning-based Matching Costs
Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai and In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2018 / 01.15
543. Accurate 3D Reconstruction from Small Motion Clip for Rolling Shutter Cameras
Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2018 / 03
542. KAIST Multi-Spectral Day/Night Data Set for Autonomous and Assisted Driving
Yukyung Choi, Namil Kim, Soonmin Hwang, Kibaek Park, Jae Shin Yoon, Kyunghwan An and In So Kweon
Transactions on Intelligent Transportation Systems (T-ITS) 2018 / 03
541. RANUS: RGB and NIR Urban Scene Dataset for Deep Scene Parsing
Gyeongmin Choe, Seong-heum Kim, Sunghoon Im, Joon-Young Lee, Srinivasa Narasimhan, In So Kweon
IEEE Robotics and Automation Letters (RAL) 2018 / 02
540. Contextually Customized Video Summaries via Natural Language
Jinsoo Choi, Tae-Hyun Oh, In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 03
539. Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution
Oleksandr Bailo , Francois Rameau , Kyungdon Joo , Jinsun Park , Oleksandr Bogdan , In So Kweon
Pattern Recognition Letters (PRL) 2018 / 02
538. Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
Dong-Jin Kim , Jinsoo Choi , Tae-Hyun Oh , Youngjin Yoon , In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 03
537. Learning Image Representations by Completing Damaged Jigsaw Puzzles
Dahun Kim , Donghyeon Cho , Donggeun Yoo , In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 05
536. StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
Sanghyun Woo, Soonmin Hwang, In So Kweon
IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 / 03
535. Multispectral Transfer Network: Unsupervised Depth Estimation for All-day Vision
Namil Kim, Yukyung Choi, Soonmin Hwang, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2018 / 02
534. Co-domain Embedding using Deep Quadruplet Network for Unseen Traffic Sign Recognition
Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2018 / 02
533. On-line Initialization and Extrinsic Calibration of an Inertial Navigation System with a Relative Preintegration Method on Manifold
Dongshin Kim, Seunghak Shin, In So Kweon
IEEE Transactions on Automation Science and Engineering (TASE) 2017 / 11
532. Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2017 / 11
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 28 Next
/ 28