Robotics and Computer Vision Lab

Publications

조회 수 1174 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.

Who's 오태현

"이것 또한 다 지나가리라"

List of Articles
585. DeepPTZ: Deep Self-Calibration for PTZ Cameras
Chaoning Zhang, Francois Rameau, Junsik Kim, Dawit Mureja Argaw, Jean-Charles Bazin, and In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV) 2020 / 03
584. Propose-and-Attend Single Shot Detector
Ho-Deok Jang, Sanghyun Woo, Philipp Benz, Jinsun Park, and In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV) 2020 / 03
583. Ring Difference Filter for Fast and Noise Robust Depth from Focus
Hae-Gon Jeon, Jaeheung Surh, Sunghoon Im, In So Kweon
IEEE Transactions Image Processing (TIP) 2019 / 8
582. Deep Iterative Frame Interpolation for Full-frame Video Stabilization
Jinsoo Choi, In So Kweon
ACM Transactions on Graphics (TOG) / SIGGRAPH Asia 2019 / 11
581. Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon
International Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019 / 11
580. Visuomotor Understanding for Representation Learning of Driving Scenes
Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon
British Machine Vision Conference (BMVC) 2019 / 9
579. Revisiting Residual Networks with Nonlinear Shortcuts
Chaoning Zhang, Francois Rameau, Seokju Lee, Junsik Kim, Philipp Benz, Dawit Mureja Argaw, Jean-Charles Bazin, In So Kweon
British Machine Vision Conference (BMVC) 2019 / 9
578. Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo
Moonyoung Lee, Yujin Heo, Jinyong Park, Hyundae Yang, Ho-Deok Jang, Philipp Benz, Hyunsub Park, In So Kweon and Jun-Ho Oh
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE 2019 / 11
577. One-Day Outdoor Photometric Stereo Using Skylight Estimation
Jiyoung Jung, Joon-Young Lee, In So Kweon
International Journal of Computer Vision (IJCV) 2019 / 8
576. Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment
Jinsun Park, Ukcheol Shin, Gyumin Shim, Kyungdon Joo, Francois Rameau, Junhyeok Kim, Dong-Geol Choi and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE 2019 / 11
575. Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment
Ukcheol Shin, Jinsun Park, Gyumin Shim, Francois Rameau, and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE 2019 / 11
574. Learning Residual Flow as Dynamic Motion from Stereo Videos
Seokju Lee, Sunghoon Im, Stephen Lin, and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE 2019 / 11
573. DISC: A Large-scale Virtual Dataset for Simulating Disaster Scenarios
Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, Dong-Geol Choi, Martial Hebert, and In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE 2019 / 11
572. Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
27th ACM International Conference on Multimedia 2019 / 10
571. Video Retargeting: Trade-off between Content Preservation and Spatio-temporal Consistency
Donghyeon Cho, Yunjae Jung, Francois Rameau, Dahun Kim, Sanghyun Woo and In So Kweon
27th ACM International Conference on Multimedia 2019 / 10
570. Segment2Regress: Monocular 3D Vehicle Localization in Two Stages
Jaesung Choe, Kyungdon Joo, Francois Rameau, Gyumin Shim, In So Kweon
Robotics: Science and Systems (RSS) 2019 / 06
569. Globally Optimal Inlier Set Maximization for Atlanta World Understanding
Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019 / 3
568. Deep Video Inpainting
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 / 07
567. Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 / 07
566. Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 / 07
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 35 Next
/ 35