Search Results for author:
Found 50 papers, 10 papers with code
Reinforcement Learning based Constrained Optimal Control: an Interpretable Reward Design
The reward function is constructed from four weighted components: a terminal constraint reward, a guidance reward, a penalty for state constraint violations, and a cost reduction incentive reward.
Causal Learning for Heterogeneous Subgroups Based on Nonlinear Causal Kernel Clustering
To address this challenge, we introduce the nonlinear Causal Kernel Clustering method designed for heterogeneous subgroup causal learning, illuminating variations in causal relationships across diverse subgroups.
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
To address this issue, we propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities.
Towards Natural Image Matting in the Wild via Real-Scenario Prior
For training objectives, the proposed regularization and trimap loss aim to retain the prior from the pre-trained model and push the matting logits extracted from the mask decoder to contain trimap-based semantic information.
Conan-embedding: General Text Embedding with More and Better Negative Samples
Embedding models are primarily trained through contrastive loss learning, with negative examples being a key component.
AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models
In this paper, we present a comprehensive overview of generative models for industrial time series from deep generative models (DGMs) to large generative models (LGMs).
Computer vision tasks for intelligent aerospace missions: An overview
Computer vision tasks are crucial for aerospace missions as they help spacecraft to understand and interpret the space environment, such as estimating position and orientation, reconstructing 3D models, and recognizing objects, which have been extensively studied to successfully carry out the missions.
Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation
In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training.
An Enhanced Differential Grouping Method for Large-Scale Overlapping Problems
In this article, we propose a two-stage enhanced grouping method for large-scale overlapping problems, called OEDG, which achieves accurate grouping while significantly reducing computational resource consumption.
Caformer: Rethinking Time Series Analysis from Causal Perspective
The spurious correlation induced by the environment confounds the causal relationships between cross-dimension and cross-time dependencies.
Humans-in-the-Building: Getting Rid of Thermostats for Optimal Thermal Comfort Control in Energy Management Systems
Given the widespread attention to individual thermal comfort, coupled with significant energy-saving potential inherent in energy management systems for optimizing indoor environments, this paper aims to introduce advanced "Humans-in-the-building" control techniques to redefine the paradigm of indoor temperature design.
A Composite Decomposition Method for Large-Scale Global Optimization
Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a non-separable variable grouping method.
Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling
The presence of nonlinearity, integer constraints, and a large number of decision variables adds complexity to this problem, posing challenges for traditional and evolutionary algorithms.
Image Fusion in Remote Sensing: An Overview and Meta Analysis
Image fusion in Remote Sensing (RS) has been a consistent demand due to its ability to turn raw images of different resolutions, sources, and modalities into accurate, complete, and spatio-temporally coherent images.
A Novel Dual-Stage Evolutionary Algorithm for Finding Robust Solutions
The primary objective of the peak-detection stage is to identify peaks in the fitness landscape of the original optimization problem.
SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting
Despite the significant strides made by graph-based networks in spatio-temporal forecasting, there remain two pivotal factors closely related to forecasting performance that need further consideration: time delays in propagation dynamics and multi-scale high-dimensional interactions.
Q-learning Based Optimal False Data Injection Attack on Probabilistic Boolean Control Networks
In this paper, we present a reinforcement learning (RL) method for solving optimal false data injection attack problems in probabilistic Boolean control networks (PBCNs) where the attacker lacks knowledge of the system model.
Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systems
ESS operators can reap benefits from energy arbitrage by optimizing operations of storage equipment.
On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data
Yet, there is no comprehensive analysis of their transferability, i. e., to which extent a model trained on a source domain can be readily applicable to a target domain.
GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture.
IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation
Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data.
CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation
However, limited by the low dynamic range of conventional cameras, images fail to capture structural details and boundary information in low-light conditions.
Causal reasoning in typical computer vision tasks
Deep learning has revolutionized the field of artificial intelligence.
Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning
Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM).
Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available.
The Second Monocular Depth Estimation Challenge
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
Reinforcement Learning Based Minimum State-flipped Control for the Reachability of Boolean Control Networks
To expedite convergence, we incorporate two improvements: i) demonstrating that previously reachable states remain reachable after adding elements to the flip set, followed by employing transfer learning, and ii) initiating each episode with special initial states whose reachability to the target state set are currently unknown.
VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud
Since 2D images provide rich semantics and scene graphs are in nature coped with languages, in this study, we propose Visual-Linguistic Semantics Assisted Training (VL-SAT) scheme that can significantly empower 3DSSG prediction models with discrimination about long-tailed and ambiguous semantic relations.
Ranked #1 on
3d scene graph generation
on 3DSSG
(using extra training data)
Random Copolymer inverse design system orienting on Accurate discovering of Antimicrobial peptide-mimetic copolymers
Herein, we develop a universal random copolymer inverse design system via multi-model copolymer representation learning, knowledge distillation and reinforcement learning.
Molecular Joint Representation Learning via Multi-modal Information
To further fusing such multi-modal imformation, the correspondence between learned chemical feature from different representation should be considered.
The Monocular Depth Estimation Challenge
This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset.
Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning
In contrast, we present a domain generalization framework based on meta-learning to dig out representative and discriminative internal properties of real hazy domains without test-time training.
Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview
Specifically, the preliminaries on few/zero-shot visual semantic segmentation, including the problem definitions, typical datasets, and technical remedies, are briefly reviewed and discussed.
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training.
Ranked #1 on
Monocular Depth Estimation
on KITTI
Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model
We further improve the robustness of the method by 1) intergrading building segmentation based on HRNetV2 into our software; and 2) having implemented a decision strategy to identify complex buildings and directly generate mesh to avoid erroneous LoD2 reconstruction from a system point of view.
Learn to Adapt for Monocular Depth Estimation
To boost the transferability of depth estimation models, we propose an adversarial depth estimation task and train the model in the pipeline of meta-learning.
Unsupervised Monocular Depth Estimation in Highly Complex Environments
Meanwhile, we further tackle the effects of unstable image transfer quality on domain adaptation, and an image adaptation approach is proposed to evaluate the quality of transferred images and re-weight the corresponding losses, so as to improve the performance of the adapted depth model.
PIAP-DF: Pixel-Interested and Anti Person-Specific Facial Action Unit Detection Net With Discrete Feedback Learning
Experimental results on the two popular AU detection datasets BP4D and DISFA prove that PIAP-DF can be the new state-of-the-art method.
Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency
Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving.
Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
This paper proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimation. The MaskNet and Boolean mask scheme are designed in this framework to eliminate the effects of occlusions and impacts of visual field changes on the reconstruction loss and adversarial loss, respectively.
When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
Then, we further review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation and robotic manipulation.
Monocular Depth Estimation Based On Deep Learning: An Overview
With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy.
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Second, we review the visual-based environmental perception and understanding methods based on deep learning, including deep learning-based monocular depth estimation, monocular ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional vSLAM frameworks.
Stability of Multi-Dimensional Switched Systems with an Application to Open Multi-Agent Systems
It shows that through a proper transformation, the seeking of the (practical) consensus performance of the open MAS with disconnected digraphs boils down to that of the (practical) stability property of an $M^3D$ system with unstable subsystems.
Deep Direct Visual Odometry
Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.
Flexible Clustering with a Sparse Mixture of Generalized Hyperbolic Distributions
Robust clustering of high-dimensional data is an important topic because clusters in real datasets are often heavy-tailed and/or asymmetric.
Text Assisted Insight Ranking Using Context-Aware Memory Network
Extracting valuable facts or informative summaries from multi-dimensional tables, i. e. insight mining, is an important task in data analysis and business intelligence.
Robust Order Scheduling in the Fashion Industry: A Multi-Objective Optimization Approach
In the fashion industry, order scheduling focuses on the assignment of production orders to appropriate production lines.
Differential Evolution with Event-Triggered Impulsive Control
In this paper, an event-triggered impulsive control scheme (ETI) is introduced to improve the performance of DE.
Model Based Clustering of High-Dimensional Binary Data
Recent work on clustering of binary data, based on a $d$-dimensional Gaussian latent variable, is extended by incorporating common factor analyzers.
