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.


List of Articles
565. Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 / 07
564. Learning Loss for Active Learning
Donggeun Yoo, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 / 07
563. Gated Bidirectional Feature Pyramid Network for Accurate One Shot Detection
Sanghyun Woo, Soonmin Hwang, Ho-Deok Jang, In So Kweon
Machine Vision And Applications (MVA) 2019 / 1
562. High-Fidelity Depth Upsampling Using the Self-Learning Framework
Inwook Shim, Tae-Hyun Oh, In So Kweon
Sensors 2019 / 01
561. DPSNet: End-to-end Deep Plane Sweep Stereo
Sunghoon Im, Hae-Gon Jeon, Stephen Lin, In So Kweon
International Conference on Learning Representations (ICLR) 2019 / 05
560. Robust Depth Estimation using Auto-Exposure Bracketing
Sunghoon Im, Hae-Gon Jeon, In So Kweon
IEEE Transaction on Image Processing (TIP) 2018 / 12
559. Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling
Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon
Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2018 / 06
558. Discriminative Feature Learning for Unsupervised Video Summarization
Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2019 / 01
557. Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles
Dahun Kim, Donghyeon Cho, In So Kweon
Association for the Advancement of Artificial Intelligence (AAAI) 2019 / 01
556. Semi-calibrated Photometric Stereo
Donghyeon Cho, Yasuyuki Matsushita, Yu-Wing Tai, and In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) /
555. Deep Convolutional Neural Network for Natural Image Matting using Initial Alpha Mattes
Donghyeon Cho, Yu-Wing Tai, In So Kweon
IEEE Transactions on Image Processing (TIP), accepted /
554. LinkNet: Relational Embedding for Scene Graph
Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
Neural Information Processing Systems (NIPS) 2018 / 12
553. CBAM: Convolutional Block Attention Module
Jongchan Park, Sanghyun Woo, Joon-Young Lee, In So Kweon
European Conference on Computer Vision (ECCV) 2018 / 09
552. BAM: Bottleneck Attention Module
Jongchan Park, Sanghyun Woo, Joon-Young Lee, In So Kweon
British Machine Vision Conference (BMVC) 2018 / 09
» 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
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 11 ... 35 Next
/ 35