Search Results for author:
Found 85 papers, 39 papers with code
HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning
To strike a balance between visual quality and application, we propose a heuristic invertible network for underwater perception enhancement, dubbed HUPE, which enhances visual quality and demonstrates flexibility in handling other downstream tasks.
Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
Transfer attacks generate significant interest for real-world black-box applications by crafting transferable adversarial examples through surrogate models.
Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy
This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures.
Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
Given a pair of captured images, subtle perturbations and distortions which go unnoticed by the human visual system tend to attack the correspondence matching, impairing the performance of image stitching algorithms.
Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation
One prevalent method to address one-shot MIS is joint registration and segmentation (JRS) with a shared encoder which mainly explores the voxel-wise correspondence between the labeled data and unlabeled data for better segmentation.
From Text to Pixels: A Context-Aware Semantic Synergy Solution for Infrared and Visible Image Fusion
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks.
Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization
Adversarial Training (AT), pivotal in fortifying the robustness of deep learning models, is extensively adopted in practical applications.
Diving into Darkness: A Dual-Modulated Framework for High-Fidelity Super-Resolution in Ultra-Dark Environments
Super-resolution tasks oriented to images captured in ultra-dark environments is a practical yet challenging problem that has received little attention.
Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation
In this work, we try to arouse the potential of enhancer + detector.
Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction
To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction.
Learning Heavily-Degraded Prior for Underwater Object Detection
Therefore, we propose a residual feature transference module (RFTM) to learn a mapping between deep representations of the heavily degraded patches of DFUI- and underwater- images, and make the mapping as a heavily degraded prior (HDP) for underwater detection.
Improving Misaligned Multi-modality Image Fusion with One-stage Progressive Dense Registration
Both stages directly estimate the respective target deformation fields.
PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation
We first conduct systematic analyses about the components of image fusion, investigating the correlation with segmentation robustness under adversarial perturbations.
Ranked #20 on
Thermal Image Segmentation
on MFN Dataset
Bilevel Generative Learning for Low-Light Vision
In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain.
Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation
Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation.
Ranked #6 on
Semantic Segmentation
on FMB Dataset
WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond
Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications.
Multi-Spectral Image Stitching via Spatial Graph Reasoning
Multi-spectral image stitching leverages the complementarity between infrared and visible images to generate a robust and reliable wide field-of-view (FOV) scene.
Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications
The complexity of learning problems, such as Generative Adversarial Network (GAN) and its variants, multi-task and meta-learning, hyper-parameter learning, and a variety of real-world vision applications, demands a deeper understanding of their underlying coupling mechanisms.
Joint Perceptual Learning for Enhancement and Object Detection in Underwater Scenarios
Based on these factual opinions, we propose a bilevel optimization formulation for jointly learning underwater object detection and image enhancement, and then unroll to a dual perception network (DPNet) for the two tasks.
Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining
Extensive experiments on synthetic benchmarks and real-world images demonstrate that the proposed RDMC delivers strong performance on the depiction of rain streaks and outperforms the state-of-the-art methods.
PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation
In light of the significant progress made in the development and application of semantic segmentation tasks, there has been increasing attention towards improving the robustness of segmentation models against natural degradation factors (e. g., rain streaks) or artificially attack factors (e. g., adversarial attack).
A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion
Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e. g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM.
Searching a Compact Architecture for Robust Multi-Exposure Image Fusion
To mitigate these limitations, this study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion.
MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes
3D object detection plays a crucial role in numerous intelligent vision systems.
Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark
Recently significant progress has been made in human action recognition and behavior prediction using deep learning techniques, leading to improved vision-based semantic understanding.
Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation
Contemporary Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast, achieving commendable results on specific datasets.
An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection
Their common characteristic of seeking complementary cues from different source images motivates us to explore the collaborative relationship between Fusion and Salient object detection tasks on infrared and visible images via an Interactively Reinforced multi-task paradigm for the first time, termed IRFS.
Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond
Recently, multi-modality scene perception tasks, e. g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems.
Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration
Since the differences in viewing range, resolution and relative position, the multi-modality sensing module composed of infrared and visible cameras needs to be registered so as to have more accurate scene perception.
Hierarchical Optimization-Derived Learning
In recent years, by utilizing optimization techniques to formulate the propagation of deep model, a variety of so-called Optimization-Derived Learning (ODL) approaches have been proposed to address diverse learning and vision tasks.
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning fields.
Practical Exposure Correction: Great Truths Are Always Simple
Improving the visual quality of the given degraded observation by correcting exposure level is a fundamental task in the computer vision community.
Breaking Free from Fusion Rule: A Fully Semantic-driven Infrared and Visible Image Fusion
To address these challenges, in this letter, we develop a semantic-level fusion network to sufficiently utilize the semantic guidance, emancipating the experimental designed fusion rules.
CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion
Infrared and visible image fusion targets to provide an informative image by combining complementary information from different sensors.
Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement
To address the above limitations, we develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model, aiming to exploit its hierarchical feature representation as an auxiliary for the low-level underwater image enhancement.
Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
Recently, Optimization-Derived Learning (ODL) has attracted attention from learning and vision areas, which designs learning models from the perspective of optimization.
Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration
Moreover, to better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM) to adaptively select more meaningful features for fusion in the Dual-path Interaction Fusion Network (DIFN).
Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields.
Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application
In past years, the minimax type single-level optimization formulation and its variations have been widely utilized to address Generative Adversarial Networks (GANs).
Toward Fast, Flexible, and Robust Low-Light Image Enhancement
Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios.
Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
This study addresses the issue of fusing infrared and visible images that appear differently for object detection.
Ranked #1 on
Object Detection
on Multispectral Dataset
Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions
Deformable image registration plays a critical role in various tasks of medical image analysis.
Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way
To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.
Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition
With estimated scene depth, our method is capable of re-rendering hazy images with different thicknesses which further benefits the training of the dehazing network.
Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement
Further, by sharing an encoder for these two components, we obtain a more lightweight version (SLiteCSDNet for short).
Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision
To partially address above issues, we establish Retinex-inspired Unrolling with Architecture Search (RUAS), a general learning framework, which not only can address low-light enhancement task, but also has the flexibility to handle other more challenging downstream vision applications.
Triple-level Model Inferred Collaborative Network Architecture for Video Deraining
In this paper, we develop a model-guided triple-level optimization framework to deduce network architecture with cooperating optimization and auto-searching mechanism, named Triple-level Model Inferred Cooperating Searching (TMICS), for dealing with various video rain circumstances.
Value-Function-based Sequential Minimization for Bi-level Optimization
We also extend BVFSM to address BLO with additional functional constraints.
Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond
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.
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
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
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.
Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community.
Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i. e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations.
Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
Low-light image enhancement plays very important roles in low-level vision field.
BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
learning to learn) has recently emerged as a promising paradigm for a variety of applications.
SMPR: Single-Stage Multi-Person Pose Regression
Existing multi-person pose estimators can be roughly divided into two-stage approaches (top-down and bottom-up approaches) and one-stage approaches.
Ranked #7 on
Multi-Person Pose Estimation
on COCO test-dev
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
In recent years, a variety of gradient-based first-order methods have been developed to solve bi-level optimization problems for learning applications.
Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
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.
Converged Deep Framework Assembling Principled Modules for CS-MRI
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
Properly modeling latent image distributions plays an important role in a variety of image-related vision problems.
Investigating Customization Strategies and Convergence Behaviors of Task-specific ADMM
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
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
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.
Task-Oriented Convex Bilevel Optimization with Latent Feasibility
This paper firstly proposes a convex bilevel optimization paradigm to formulate and optimize popular learning and vision problems in real-world scenarios.
Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions
Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.
A Bridging Framework for Model Optimization and Deep Propagation
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
In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics.
A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI
Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications.
Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-convex Optimization
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
Enhancing visual qualities of images plays very important roles in various vision and learning applications.
On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems
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.
Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond
Blind image deblurring plays a very important role in many vision and multimedia applications.
Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization
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.
Unsupervised representation learning with long-term dynamics for skeleton based action recognition
In recent years, skeleton based action recognition is becoming an increasingly attractive alternative to existing video-based approaches, beneficial from its robust and comprehensive 3D information.
Self-Reinforced Cascaded Regression for Face Alignment
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.
Proximal Alternating Direction Network: A Globally Converged Deep Unrolling Framework
Deep learning models have gained great success in many real-world applications.
Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond
However, they may fail when their assumptions are not valid on specific images.
An Optimization Framework with Flexible Inexact Inner Iterations for Nonconvex and Nonsmooth Programming
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
In this paper, we propose a novel sparse coding and counting method under Bayesian framwork for visual tracking.
Adaptive Partial Differential Equation Learning for Visual Saliency Detection
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.
Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning
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.
Kernel Estimation from Salient Structure for Robust Motion Deblurring
One effective way to eliminate these details is to apply image denoising model based on the Total Variation (TV).
Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation
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
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 $n$.
