Mengfan Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mengfan Xu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Wei Huang
School of Communication & Information Engineering, Shanghai University, Shanghai, P. R. China
2 shared publications - Kai-Li Li
Communication and Information Engineering, Shanghai University, Shanghai 200444, China
1 shared publication - Rui Huang
School of Communication and Information Engineering, Shanghai University, Shanghai, China
1 shared publication - Xiaofeng Lu
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
1 shared publication - Zhuoming Gu
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
1 shared publication
Latest Publications
- Open Access
- 27 March 2025
- Published by MDPI AG in Electronics
- Vol. 14 (7) , 1338
Spatial–Adaptive Replay for Foreground Classes in Class-Incremental Semantic Segmentation
Class-Incremental Semantic Segmentation (CISS) addresses the challenge of catastrophic forgetting in semantic segmentation models. In autonomous driving scenarios, the model can learn the background class information from the new data due to the repetition of many structural background classes in new data. Traditional replay-based methods store the original pixels of these background classes from old data, resulting in low memory efficiency. To enhance memory efficiency, we propose Spatial–Adaptive replay for Foreground objects (SAF), a method that stores only foreground-class pixels and their spatial information. In addition, Spatial–Adaptive Mix-up (SAM) is designed in the proposed method, based on the spatial distribution characteristics of the foreground classes. Spatial–adaptive alignment ensures that foreground objects are mixed with new samples in a reasonable spatial arrangement to help the model learn critical contextual information. Experiments on the Cityscapes and BDD100K datasets show that the proposed method obtains competitive results in class-incremental semantic segmentation tasks for autonomous driving scenarios.
- 27 March 2025
- Published by MDPI AG in Electronics
- Vol. 14 (7) , 1338
Open AccessSpatial–Adaptive Replay for Foreground Classes in Class-Incremental Semantic Segmentation
Class-Incremental Semantic Segmentation (CISS) addresses the challenge of catastrophic forgetting in semantic segmentation models. In autonomous driving scenarios, the model can learn the background class information from the new data due to the repetition of many structural background classes in new data. Traditional replay-based methods store the original pixels of these background classes from old data, resulting in low memory efficiency. To enhance memory efficiency, we propose Spatial–Adaptive replay for Foreground objects (SAF), a method that stores only foreground-class pixels and their spatial information. In addition, Spatial–Adaptive Mix-up (SAM) is designed in the proposed method, based on the spatial distribution characteristics of the foreground classes. Spatial–adaptive alignment ensures that foreground objects are mixed with new samples in a reasonable spatial arrangement to help the model learn critical contextual information. Experiments on the Cityscapes and BDD100K datasets show that the proposed method obtains competitive results in class-incremental semantic segmentation tasks for autonomous driving scenarios.
- Open Access
- 29 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4445
Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion
Low-light image enhancement is a challenging task in non-uniform low-light conditions, often resulting in local overexposure, noise amplification, and color distortion. To obtain satisfactory enhancement results, most models must resort to carefully selected paired or multi-exposure data sets. In this paper, we propose a self-supervised framework for non-uniform low-light image enhancement to address these issues, only requiring low-light images on their own for training. We first design a robust Retinex model-based image exposure enhancement network (EENet) to obtain global brightness enhancement and noise removal of images by carefully designing the loss function of each decomposition map. Then, to correct overexposed areas in the enhanced image, we incorporate the inverse image of the low-light image for enhancement using EENet. Furthermore, a three-branch asymmetric exposure fusion network (TAFNet) is designed. The two enhanced images and the original image are used as the TAFNet inputs to obtain a globally well-exposed and detail-rich image. Experimental results demonstrate that our framework outperforms some state-of-the-art methods in visual and quantitative comparisons.
- 29 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4445
Open AccessSelf-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion
Low-light image enhancement is a challenging task in non-uniform low-light conditions, often resulting in local overexposure, noise amplification, and color distortion. To obtain satisfactory enhancement results, most models must resort to carefully selected paired or multi-exposure data sets. In this paper, we propose a self-supervised framework for non-uniform low-light image enhancement to address these issues, only requiring low-light images on their own for training. We first design a robust Retinex model-based image exposure enhancement network (EENet) to obtain global brightness enhancement and noise removal of images by carefully designing the loss function of each decomposition map. Then, to correct overexposed areas in the enhanced image, we incorporate the inverse image of the low-light image for enhancement using EENet. Furthermore, a three-branch asymmetric exposure fusion network (TAFNet) is designed. The two enhanced images and the original image are used as the TAFNet inputs to obtain a globally well-exposed and detail-rich image. Experimental results demonstrate that our framework outperforms some state-of-the-art methods in visual and quantitative comparisons.