Search Results for author: Risheng Liu

Found 36 papers, 8 papers with code

Value-Function-based Sequential Minimization for Bi-level Optimization

1 code implementation11 Oct 2021 Risheng Liu, Xuan Liu, Shangzhi Zeng, Jin Zhang, Yixuan Zhang

To our best knowledge, this is the first gradient-based algorithm that can solve different kinds of BLO problems (e. g., optimistic, pessimistic and with constraints) all with solid convergence guarantees.

Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond

no code implementations1 Oct 2021 Risheng Liu, Yaohua Liu, Shangzhi Zeng, Jin Zhang

In particular, by introducing an auxiliary as initialization to guide the optimization dynamics and designing a pessimistic trajectory truncation operation, we construct a reliable approximate version of the original BLO in the absence of LLC hypothesis.

bilevel optimization

A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization

no code implementations15 Jun 2021 Risheng Liu, Xuan Liu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang

Bi-level optimization model is able to capture a wide range of complex learning tasks with practical interest.

A General Descent Aggregation Framework for Gradient-based Bi-level Optimization

no code implementations16 Feb 2021 Risheng Liu, Pan Mu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang

In this work, we formulate BLOs from an optimistic bi-level viewpoint and establish a new gradient-based algorithmic framework, named Bi-level Descent Aggregation (BDA), to partially address the above issues.

Meta-Learning

Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond

1 code implementation27 Jan 2021 Risheng Liu, Jiaxin Gao, Jin Zhang, Deyu Meng, Zhouchen Lin

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community.

Hierarchical structure Meta-Learning +1

Learning Optimization-inspired Image Propagation with Control Mechanisms and Architecture Augmentations for Low-level Vision

no code implementations10 Dec 2020 Risheng Liu, Zhu Liu, Pan Mu, Zhouchen Lin, Xin Fan, Zhongxuan Luo

In recent years, building deep learning models from optimization perspectives has becoming a promising direction for solving low-level vision problems.

BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning

1 code implementation28 Sep 2020 Yaohua Liu, Risheng Liu

learning to learn) has recently emerged as a promising paradigm for a variety of applications.

bilevel optimization Meta-Learning

SMPR: Single-Stage Multi-Person Pose Regression

1 code implementation28 Jun 2020 Junqi Lin, Huixin Miao, Junjie Cao, Zhixun Su, Risheng Liu

Existing multi-person pose estimators can be roughly divided into two-stage approaches (top-down and bottom-up approaches) and one-stage approaches.

Multi-Person Pose Estimation

A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton

no code implementations ICML 2020 Risheng Liu, Pan Mu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang

In recent years, a variety of gradient-based first-order methods have been developed to solve bi-level optimization problems for learning applications.

Meta-Learning

Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond

2 code implementations30 Apr 2020 Risheng Liu, Zi Li, Xin Fan, Chenying Zhao, Hao Huang, Zhongxuan Luo

We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches.

Image Registration Semantic Segmentation

Converged Deep Framework Assembling Principled Modules for CS-MRI

no code implementations29 Oct 2019 Risheng Liu, Yuxi Zhang, Shichao Cheng, Zhongxuan Luo, Xin Fan

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) significantly accelerates MR data acquisition at a sampling rate much lower than the Nyquist criterion.

Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling

no code implementations18 Oct 2019 Risheng Liu, Pan Mu, Jian Chen, Xin Fan, Zhongxuan Luo

Properly modeling latent image distributions plays an important role in a variety of image-related vision problems.

Deblurring

Investigating Customization Strategies and Convergence Behaviors of Task-specific ADMM

no code implementations24 Sep 2019 Risheng Liu, Pan Mu, Jin Zhang

Alternating Direction Method of Multiplier (ADMM) has been a popular algorithmic framework for separable optimization problems with linear constraints.

Semi-supervised Skin Detection by Network with Mutual Guidance

no code implementations ICCV 2019 Yi He, Jiayuan Shi, Chuan Wang, Haibin Huang, Jiaming Liu, Guanbin Li, Risheng Liu, Jue Wang

In this paper we present a new data-driven method for robust skin detection from a single human portrait image.

Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation

no code implementations17 Jul 2019 Risheng Liu, Long Ma, Yuxi Zhang, Xin Fan, Zhongxuan Luo

Plenty of experimental results of underexposed image correction demonstrate that our proposed method performs favorably against the state-of-the-art methods on both subjective and objective assessments.

Face Detection Single Image Haze Removal

Bilevel Integrative Optimization for Ill-posed Inverse Problems

no code implementations6 Jul 2019 Risheng Liu, Long Ma, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang

Classical optimization techniques often formulate the feasibility of the problems as set, equality or inequality constraints.

Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions

1 code implementation15 Jan 2019 Risheng Liu, Xin Fan, Ming Zhu, Minjun Hou, Zhongxuan Luo

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.

Image Enhancement Object Detection

A Bridging Framework for Model Optimization and Deep Propagation

no code implementations NeurIPS 2018 Risheng Liu, Shichao Cheng, Xiaokun Liu, Long Ma, Xin Fan, Zhongxuan Luo

Different from these existing network based iterations, which often lack theoretical investigations, we provide strict convergence analysis for PODM in the challenging nonconvex and nonsmooth scenarios.

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

no code implementations12 Nov 2018 Jun Wen, Risheng Liu, Nenggan Zheng, Qian Zheng, Zhefeng Gong, Junsong Yuan

In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics.

Unsupervised Domain Adaptation

A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI

no code implementations9 Nov 2018 Risheng Liu, Yuxi Zhang, Shichao Cheng, Xin Fan, Zhongxuan Luo

Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications.

Compressive Sensing

Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-convex Optimization

no code implementations5 Nov 2018 Yiyang Wang, Risheng Liu, Long Ma, Xiaoliang Song

Integrating both numerical algorithms and advanced techniques together, TECU is proposed in a unified framework for solving a class of non-convex problems.

Learning Converged Propagations with Deep Prior Ensemble for Image Enhancement

1 code implementation9 Oct 2018 Risheng Liu, Long Ma, Yiyang Wang, Lei Zhang

Enhancing visual qualities of images plays very important roles in various vision and learning applications.

Image Enhancement

On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems

no code implementations16 Aug 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhouchen Lin, Zhongxuan Luo

Moreover, there is a lack of rigorous analysis about the convergence behaviors of these reimplemented iterations, and thus the significance of such methods is a little bit vague.

Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization

no code implementations28 Apr 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhongxuan Luo

Operator splitting methods have been successfully used in computational sciences, statistics, learning and vision areas to reduce complex problems into a series of simpler subproblems.

Deblurring

Self-Reinforced Cascaded Regression for Face Alignment

no code implementations23 Nov 2017 Xin Fan, Risheng Liu, Kang Huyan, Yuyao Feng, Zhongxuan Luo

Cascaded regression is prevailing in face alignment thanks to its accuracy and robustness, but typically demands manually annotated examples having low discrepancy between shape-indexed features and shape updates.

Face Alignment

An Optimization Framework with Flexible Inexact Inner Iterations for Nonconvex and Nonsmooth Programming

no code implementations28 Feb 2017 Yiyang Wang, Risheng Liu, Xiaoliang Song, Zhixun Su

In recent years, numerous vision and learning tasks have been (re)formulated as nonconvex and nonsmooth programmings(NNPs).

Sparse Coding and Counting for Robust Visual Tracking

no code implementations28 May 2016 Risheng Liu, Jing Wang, Yiyang Wang, Zhixun Su, Yu Cai

In this paper, we propose a novel sparse coding and counting method under Bayesian framwork for visual tracking.

Visual Tracking

Adaptive Partial Differential Equation Learning for Visual Saliency Detection

no code implementations CVPR 2014 Risheng Liu, Junjie Cao, Zhouchen Lin, Shiguang Shan

Then by optimizing a discrete submodular function constrained with this LESD and a uniform matroid, the saliency seeds (i. e., boundary conditions) can be learnt for this image, thus achieving an optimal PDE system to model the evolution of visual saliency.

Saliency Detection

Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning

no code implementations18 Oct 2013 Zhouchen Lin, Risheng Liu, Huan Li

However, the traditional alternating direction method (ADM) and its linearized version (LADM, obtained by linearizing the quadratic penalty term) are for the two-block case and cannot be naively generalized to solve the multi-block case.

Distributed Computing

Kernel Estimation from Salient Structure for Robust Motion Deblurring

no code implementations5 Dec 2012 Jinshan Pan, Risheng Liu, Zhixun Su, Xianfeng GU

One effective way to eliminate these details is to apply image denoising model based on the Total Variation (TV).

Blind Image Deblurring Image Denoising +1

Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation

no code implementations NeurIPS 2011 Zhouchen Lin, Risheng Liu, Zhixun Su

It suffers from $O(n^3)$ computation complexity due to the matrix-matrix multiplications and matrix inversions, even if partial SVD is used.

Optimization and Control

Solving Principal Component Pursuit in Linear Time via $l_1$ Filtering

no code implementations26 Aug 2011 Risheng Liu, Zhouchen Lin, Siming Wei, Zhixun Su

In this paper, we propose a novel algorithm, called $l_1$ filtering, for \emph{exactly} solving PCP with an $O(r^2(m+n))$ complexity, where $m\times n$ is the size of data matrix and $r$ is the rank of the matrix to recover, which is supposed to be much smaller than $m$ and $n$.

Cannot find the paper you are looking for? You can Submit a new open access paper.