Jin Jiang
Jin Jiang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Chentao Zhang
Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen 361102, China
3 shared publications - Jianhuan Zhang
Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen 361102, China
2 shared publications - Maozhang Ye
Applied Technology Engineering Center of Fujian Provincial Higher Education for Visual Perception and Intelligent Analysis, Quanzhou Vocational College of Economics and Business, Quanzhou 362000, China
2 shared publications - Chunlai Li
Shenzhen Institute of Peking University, Shenzhen 518057, China
1 shared publication - Fenghe Yang
Zhang Jiang Laboratory, Shanghai 201210, China
1 shared publication - Gaofeng Zheng
Pen‐Tung Sah Institute of Micro‐Nano Science and Technology Xiamen University Xiamen China
1 shared publication
Latest Publications
- Open Access
TAMCA: Time-Aware Multi-Scale Convolutional Attention for Multi-Class Industrial Anomaly Detection
In multi-class industrial anomaly detection, latent diffusion models commonly use the same attention and receptive-field configuration across all noise stages. This stage-invariant design makes it difficult to balance global structure recovery at high noise levels with local detail preservation at low noise levels, which may lead to structural drift, over-smoothing, and unstable anomaly maps. To address this issue, we propose TAMCA, a time-aware multi-scale convolutional attention framework for diffusion-based anomaly detection. In TAMCA, a Multi-Scale Convolutional Attention module (MSCA) is embedded into the denoising network to jointly model local textures and long-range contextual dependencies through local depthwise convolution and decomposed large-kernel convolution. To further adapt contextual modeling to different denoising stages, diffusion timestep embeddings are mapped into gating coefficients, which selectively regulate the contribution of the large-kernel context branch according to the noise level. During inference, Diffusion-aware Consistency Ensembling (DiCE) estimates multi-view reliability through median consensus and performs reliability-weighted fusion to suppress view-specific false responses. Experiments on MVTec-AD and VisA show that TAMCA achieves pixel-level AUROC values of 97.2% and 97.0%, respectively, with consistent improvements in pixel-level AP, F1max, and PRO.
Open AccessTAMCA: Time-Aware Multi-Scale Convolutional Attention for Multi-Class Industrial Anomaly Detection
In multi-class industrial anomaly detection, latent diffusion models commonly use the same attention and receptive-field configuration across all noise stages. This stage-invariant design makes it difficult to balance global structure recovery at high noise levels with local detail preservation at low noise levels, which may lead to structural drift, over-smoothing, and unstable anomaly maps. To address this issue, we propose TAMCA, a time-aware multi-scale convolutional attention framework for diffusion-based anomaly detection. In TAMCA, a Multi-Scale Convolutional Attention module (MSCA) is embedded into the denoising network to jointly model local textures and long-range contextual dependencies through local depthwise convolution and decomposed large-kernel convolution. To further adapt contextual modeling to different denoising stages, diffusion timestep embeddings are mapped into gating coefficients, which selectively regulate the contribution of the large-kernel context branch according to the noise level. During inference, Diffusion-aware Consistency Ensembling (DiCE) estimates multi-view reliability through median consensus and performs reliability-weighted fusion to suppress view-specific false responses. Experiments on MVTec-AD and VisA show that TAMCA achieves pixel-level AUROC values of 97.2% and 97.0%, respectively, with consistent improvements in pixel-level AP, F1max, and PRO.
- Open Access
FAFMNet: Feature Attention Fusion Multimodal Network of Road Potholes for Mobile Robot
Road potholes pose a considerable threat to mobile robots, which are generally less stable than conventional vehicles and may become trapped or overturned when traversing damaged road surfaces. Accurate semantic segmentation of road potholes is therefore essential for safe and reliable robot navigation. To address this requirement, multimodal fusion methods using RGB (Red, Green, Blue) and disparity images have been developed for pothole detection. Nevertheless, these methods still face challenges in detecting small potholes and delineating their boundaries precisely. To overcome these limitations, we propose a novel multimodal fusion network for road-pothole semantic segmentation. Specifically, we design a feature fusion module that integrates global context and local details to fully exploit the complementary information provided by RGB and disparity images. This design improves multimodal feature interaction and enhances boundary segmentation accuracy. Furthermore, we develop three feature attention fusion modules by incorporating multiple complementary attention mechanisms into the fusion module. These modules improve small-pothole detection by focusing on informative features, emphasizing target regions, and reducing information loss. We evaluate the proposed network on a small-pothole subset of Pothole-600 under identical hardware settings and backbone configurations for all experimental models. On the small-pothole subset of Pothole-600, FAFMNet achieves 90.22% mPre, 92.32% mRec, 98.73% mAcc, 91.26% mF1, and 83.93% mIoU, outperforming the state-of-the-art method by 1.87 percentage points in mF1 and 3.12 percentage points in mIoU. A paired statistical test over three independent runs further confirms that the improvement over the baseline is statistically significant ().Open AccessFAFMNet: Feature Attention Fusion Multimodal Network of Road Potholes for Mobile Robot
Road potholes pose a considerable threat to mobile robots, which are generally less stable than conventional vehicles and may become trapped or overturned when traversing damaged road surfaces. Accurate semantic segmentation of road potholes is therefore essential for safe and reliable robot navigation. To address this requirement, multimodal fusion methods using RGB (Red, Green, Blue) and disparity images have been developed for pothole detection. Nevertheless, these methods still face challenges in detecting small potholes and delineating their boundaries precisely. To overcome these limitations, we propose a novel multimodal fusion network for road-pothole semantic segmentation. Specifically, we design a feature fusion module that integrates global context and local details to fully exploit the complementary information provided by RGB and disparity images. This design improves multimodal feature interaction and enhances boundary segmentation accuracy. Furthermore, we develop three feature attention fusion modules by incorporating multiple complementary attention mechanisms into the fusion module. These modules improve small-pothole detection by focusing on informative features, emphasizing target regions, and reducing information loss. We evaluate the proposed network on a small-pothole subset of Pothole-600 under identical hardware settings and backbone configurations for all experimental models. On the small-pothole subset of Pothole-600, FAFMNet achieves 90.22% mPre, 92.32% mRec, 98.73% mAcc, 91.26% mF1, and 83.93% mIoU, outperforming the state-of-the-art method by 1.87 percentage points in mF1 and 3.12 percentage points in mIoU. A paired statistical test over three independent runs further confirms that the improvement over the baseline is statistically significant (). - Open Access
Unsupervised Domain Adaptation with Multimodal Fusion for Monocular 3D Object Detection
This paper presents UM3D, an end-to-end unsupervised domain adaptation framework for monocular 3D object detection. Monocular 3D object detection is appealing due to its low cost, yet it suffers from limited depth cues and poor cross-domain generalization when labeled data are scarce. Existing Pseudo-LiDAR methods require supervised training and propagate depth estimation errors to downstream detection, while current unsupervised domain adaptation (UDA) approaches exploit only a single modality and lack effective pseudo-label quality control. UM3D addresses these limitations through two key designs: (1) a quality-aware pseudo-label generation strategy with object-level random scaling and a memory bank refinement mechanism; and (2) an end-to-end differentiable pipeline that integrates multimodal fusion of image and Pseudo-LiDAR features with a multi-network consistency loss, which jointly optimizes depth estimation and 3D detection via backpropagation. Notably, the entire pipeline requires only a single monocular camera at inference; the Pseudo-LiDAR representation is generated internally from the same image, and thus the multimodal fusion integrates image and Pseudo-LiDAR features without requiring additional sensors. Extensive experiments across KITTI, nuScenes, Waymo, and Lyft demonstrate that UM3D generally outperforms existing UDA methods. In particular, a 19.30% relative improvement is achieved under easy conditions through end-to-end joint training compared to independent depth estimation, and up to 76.81% of the domain gap is closed on the WOD → KITTI benchmark.Open AccessUnsupervised Domain Adaptation with Multimodal Fusion for Monocular 3D Object Detection
This paper presents UM3D, an end-to-end unsupervised domain adaptation framework for monocular 3D object detection. Monocular 3D object detection is appealing due to its low cost, yet it suffers from limited depth cues and poor cross-domain generalization when labeled data are scarce. Existing Pseudo-LiDAR methods require supervised training and propagate depth estimation errors to downstream detection, while current unsupervised domain adaptation (UDA) approaches exploit only a single modality and lack effective pseudo-label quality control. UM3D addresses these limitations through two key designs: (1) a quality-aware pseudo-label generation strategy with object-level random scaling and a memory bank refinement mechanism; and (2) an end-to-end differentiable pipeline that integrates multimodal fusion of image and Pseudo-LiDAR features with a multi-network consistency loss, which jointly optimizes depth estimation and 3D detection via backpropagation. Notably, the entire pipeline requires only a single monocular camera at inference; the Pseudo-LiDAR representation is generated internally from the same image, and thus the multimodal fusion integrates image and Pseudo-LiDAR features without requiring additional sensors. Extensive experiments across KITTI, nuScenes, Waymo, and Lyft demonstrate that UM3D generally outperforms existing UDA methods. In particular, a 19.30% relative improvement is achieved under easy conditions through end-to-end joint training compared to independent depth estimation, and up to 76.81% of the domain gap is closed on the WOD → KITTI benchmark. - Open Access
Hierarchical optimization control strategy of hybrid electric vehicle platoon under communication failure
- Open Access
- 13 February 2025
- Published by MDPI AG in Preprints.org
The Frequency Response Characteristics of Ge-on-Si Photodetectors Under High Incident Power
This study explores the mechanisms responsible for the bandwidth reduction observed in Ge-on-Si photodetectors under high incident light power. We investigate the impact of the carrier-screening effect on the bandwidth through simulations, and we mitigate this effect by increasing the applied bias voltage. The increase in the concentration of photogenerated carriers leads to a reduction in the carrier saturation drift velocity, which reduces the bandwidth of the Ge-on-Si photodetector; this phenomenon is studied for the first time. The bandwidth is determined primarily by the carrier saturation drift velocity when the incident light power is below 2.5 mW, and the decrease in bandwidth that is calculated based on the decrease in carrier saturation drift velocity is consistent with the experimental results. However, when the incident light power exceeds 3 mW, both the carrier-screening effect and the reduction in the carrier saturation drift velocity contribute to the bandwidth reduction. This study provides a good theoretical guicdance for the design of high-power Ge-on-Si photodetectors.
- 13 February 2025
- Published by MDPI AG in Preprints.org
Open AccessThe Frequency Response Characteristics of Ge-on-Si Photodetectors Under High Incident Power
This study explores the mechanisms responsible for the bandwidth reduction observed in Ge-on-Si photodetectors under high incident light power. We investigate the impact of the carrier-screening effect on the bandwidth through simulations, and we mitigate this effect by increasing the applied bias voltage. The increase in the concentration of photogenerated carriers leads to a reduction in the carrier saturation drift velocity, which reduces the bandwidth of the Ge-on-Si photodetector; this phenomenon is studied for the first time. The bandwidth is determined primarily by the carrier saturation drift velocity when the incident light power is below 2.5 mW, and the decrease in bandwidth that is calculated based on the decrease in carrier saturation drift velocity is consistent with the experimental results. However, when the incident light power exceeds 3 mW, both the carrier-screening effect and the reduction in the carrier saturation drift velocity contribute to the bandwidth reduction. This study provides a good theoretical guicdance for the design of high-power Ge-on-Si photodetectors.