Hangcheng Dong
YOU?
Author Swipe
View article: Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defects
Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defects Open
Industrial surface defect inspection for sample-wise quality control (QC) must simultaneously decide whether a given sample contains defects and localize those defects spatially. In real production lines, extreme foreground-background imba…
View article: Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception
Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception Open
Surface defect detection plays a critical role in industrial quality inspection. Recent advances in artificial intelligence have significantly enhanced the automation level of detection processes. However, conventional semantic segmentatio…
View article: A unified approach for weakly supervised crack detection via affine transformation and pseudo label refinement
A unified approach for weakly supervised crack detection via affine transformation and pseudo label refinement Open
View article: Precision and Efficiency in Dam Crack Inspection: A Lightweight Object Detection Method Based on Joint Distillation for Unmanned Aerial Vehicles (UAVs)
Precision and Efficiency in Dam Crack Inspection: A Lightweight Object Detection Method Based on Joint Distillation for Unmanned Aerial Vehicles (UAVs) Open
Dams in their natural environment will gradually develop cracks and other forms of damage. If not detected and repaired in time, the structural strength of the dam may be reduced, and it may even collapse. Repairing cracks and defects in d…
View article: Interpretability as Approximation: Understanding Black-Box Models by Decision Boundary
Interpretability as Approximation: Understanding Black-Box Models by Decision Boundary Open
Currently, interpretability methods focus more on less objective human-understandable semantics. To objectify and standardize interpretability research, in this study, we provide notions of interpretability based on approximation theory. W…
View article: No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks
No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks Open
Biologically, the brain does not rely on a single type of neuron that universally functions in all aspects. Instead, it acts as a sophisticated designer of task-based neurons. In this study, we address the following question: since the hum…
View article: Cloud-Rain: Point Cloud Analysis with Reflectional Invariance
Cloud-Rain: Point Cloud Analysis with Reflectional Invariance Open
View article: Continuous gradient fusion class activation mapping: segmentation of laser-induced damage on large-aperture optics in dark-field images
Continuous gradient fusion class activation mapping: segmentation of laser-induced damage on large-aperture optics in dark-field images Open
Segmenting dark-field images of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmen…
View article: Weakly-Supervised Video Anomaly Detection with MTDA-Net
Weakly-Supervised Video Anomaly Detection with MTDA-Net Open
Weakly supervised anomalous behavior detection is a popular area at present. Compared to semi-supervised anomalous behavior detection, weakly-supervised learning both eliminates the need to crop videos and solves the problem of semi-superv…
View article: Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise
Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise Open
Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weakly supervised learning. A major limitation to the performan…
View article: CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics
CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics Open
Online segmentation of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmentation al…
View article: MTR-SAM: Visual Multimodal Text Recognition and Sentiment Analysis in Public Opinion Analysis on the Internet
MTR-SAM: Visual Multimodal Text Recognition and Sentiment Analysis in Public Opinion Analysis on the Internet Open
Existing methods for monitoring internet public opinion rely primarily on regular crawling of textual information on web pages but cannot quickly and accurately acquire and identify textual information in images and videos and discriminate…
View article: Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance
Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance Open
The networks for point cloud tasks are expected to be invariant when the point clouds are affinely transformed such as rotation and reflection. So far, relative to the rotational invariance that has been attracting major research attention…
View article: Multi-task neural network blind deconvolution and its application to bearing fault feature extraction
Multi-task neural network blind deconvolution and its application to bearing fault feature extraction Open
Blind deconvolution (BD) is an effective method to extract fault-related characteristics from vibration signals. Previous researches focused on two primary approaches to improve the robustness and effectiveness of BD methods: developing ne…
View article: One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks
One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks Open
Inspired by neuronal diversity in the biological neural system, a plethora of studies proposed to design novel types of artificial neurons and introduce neuronal diversity into artificial neural networks. Recently proposed quadratic neuron…
View article: Multi-task Neural Network Blind Deconvolution and its Application to Bearing Fault Feature Extraction
Multi-task Neural Network Blind Deconvolution and its Application to Bearing Fault Feature Extraction Open
Blind deconvolution (BD) is one of the effective methods that help pre-process vibration signals and assist in bearing fault diagnosis. Currently, most BD methods design an optimization criterion and use frequency or time domain informatio…
View article: Predicting Propellant Properties of Boron-Based Hypergolic Ionic Liquids via Machine Learning
Predicting Propellant Properties of Boron-Based Hypergolic Ionic Liquids via Machine Learning Open
Boron-based hypergolic ionic liquids (HILs) have gained increasing attention in the field of propellants due to the low toxicity, high energy density, and short ignition delay time. However, the performance of propellants based on boron-ba…
View article: Deep Learning-Based Remaining Useful Life Estimation of Bearings with Time-Frequency Information
Deep Learning-Based Remaining Useful Life Estimation of Bearings with Time-Frequency Information Open
In modern industrial production, the prediction ability of remaining useful life of bearings directly affects the safety and stability of the system. Traditional methods require rigorous physical modeling and perform poorly for complex sys…
View article: Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis
Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis Open
Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits. Recently, machine learning, represented by deep learning, has made great progress in bearing fault diagno…
View article: SAL-CNN: Estimate the Remaining Useful Life of Bearings Using Time-frequency Information
SAL-CNN: Estimate the Remaining Useful Life of Bearings Using Time-frequency Information Open
In modern industrial production, the prediction ability of the remaining useful life (RUL) of bearings directly affects the safety and stability of the system. Traditional methods require rigorous physical modeling and perform poorly for c…
View article: Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection
Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection Open
Inspired by the complexity and diversity of biological neurons, a quadratic neuron is proposed to replace the inner product in the current neuron with a simplified quadratic function. Employing such a novel type of neurons offers a new per…
View article: Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation
Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation Open
Recently, the interpretability of deep learning has attracted a lot of attention. A plethora of methods have attempted to explain neural networks by feature visualization, saliency maps, model distillation, and so on. However, it is hard f…
View article: How to Explain Neural Networks: A perspective of data space division.
How to Explain Neural Networks: A perspective of data space division. Open
Interpretability of intelligent algorithms represented by deep learning has been yet an open problem. We discuss the shortcomings of the existing explainable method based on the two attributes of explanation, which are called completeness …
View article: How to Explain Neural Networks: an Approximation Perspective
How to Explain Neural Networks: an Approximation Perspective Open
The lack of interpretability has hindered the large-scale adoption of AI technologies. However, the fundamental idea of interpretability, as well as how to put it into practice, remains unclear. We provide notions of interpretability based…