Cheng Pang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cheng Pang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Rushi Lan
Guilin University of Electronic Technology
12 shared publications - Xiaonan Luo
Guilin University of Electronic Technology, Guilin, China
4 shared publications - Zhenbing Liu
Guilin University of Electronic Technology
3 shared publications - Dingzhou Xie
Guilin University of Electronic Technology, Guilin, China
2 shared publications - Guanhua Wu
Guilin University of Electronic Technology
2 shared publications - Huimin Lu
Southeast University
2 shared publications
Latest Publications
- 4 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
GMM-based discriminative feature embedding framework for unsupervised fine-grained image retrieval
- 4 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
GMM-based discriminative feature embedding framework for unsupervised fine-grained image retrieval
- Open Access
Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection
Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined to refining single-layer or fusing dual-layer features, overlooking the rich inter-layer dependencies across multi-scale representations. This limits their ability to capture comprehensive contextual information essential for detecting objects with large scale variations. In this paper, we propose a novel Cross-Layer Feature Self-Attention Module (CFSAM), which holistically models both local and global dependencies within multi-scale feature maps. CFSAM consists of three key components: a convolutional local feature extractor, a Transformer-based global modeling unit that efficiently captures cross-layer interactions, and a feature fusion mechanism to restore and enhance the original representations. When integrated into the SSD300 framework, CFSAM significantly boosts detection performance, achieving 78.6% mAP on PASCAL VOC (vs. 75.5% baseline) and 52.1% mAP on COCO (vs. 43.1% baseline), outperforming existing attention modules. Moreover, the module accelerates convergence during training without introducing substantial computational overhead. Our work highlights the importance of explicit cross-layer attention modeling in advancing multi-scale object detection.
Open AccessCross-Layer Feature Self-Attention Module for Multi-Scale Object Detection
Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined to refining single-layer or fusing dual-layer features, overlooking the rich inter-layer dependencies across multi-scale representations. This limits their ability to capture comprehensive contextual information essential for detecting objects with large scale variations. In this paper, we propose a novel Cross-Layer Feature Self-Attention Module (CFSAM), which holistically models both local and global dependencies within multi-scale feature maps. CFSAM consists of three key components: a convolutional local feature extractor, a Transformer-based global modeling unit that efficiently captures cross-layer interactions, and a feature fusion mechanism to restore and enhance the original representations. When integrated into the SSD300 framework, CFSAM significantly boosts detection performance, achieving 78.6% mAP on PASCAL VOC (vs. 75.5% baseline) and 52.1% mAP on COCO (vs. 43.1% baseline), outperforming existing attention modules. Moreover, the module accelerates convergence during training without introducing substantial computational overhead. Our work highlights the importance of explicit cross-layer attention modeling in advancing multi-scale object detection.
- 4 April 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (33) , 41479-41493
Feature reinforcement meets feature suppression: a hierarchical bilateral method for fine-grained visual classification
- 4 April 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (33) , 41479-41493
Feature reinforcement meets feature suppression: a hierarchical bilateral method for fine-grained visual classification
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (1) , 90-103
Single Traffic Image Deraining via Similarity-Diversity Model
Single traffic image deraining technology based on deep learning is a vital branch of image preprocessing, which is of great help to intelligent monitoring systems and driving navigation system. It is well understood that established deraining methods are derived based on one specific imaging model, neglecting the underlying correlations between different weather models and thereby limiting the applicability of these standard methods in real scenarios. To ameliorate this issue, in this work, we first explore the inherent relationship between a rain model and the haze one established up to date. We discover that these two models experience similar degradations in the low-frequency components (i.e., similarity) but diverse degradations in the high-frequency areas (i.e., diversity). Based on these observations, we develop a Similarity-Diversity model to describe these characteristics. Afterwards, we introduce a novel deep neural network to restore the rain-free background embedding the similarity-diversity model, namely deep similarity-diversity network (DSDNet). Extensive experiments have been conducted to evaluate our proposed method that outperforms the other state of the art deraining techniques. On the other hand, we deploy the proposed algorithm with Google Vision API for object recognition, which also obtains satisfactory results both qualitatively and quantitatively.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (1) , 90-103
Single Traffic Image Deraining via Similarity-Diversity Model
Single traffic image deraining technology based on deep learning is a vital branch of image preprocessing, which is of great help to intelligent monitoring systems and driving navigation system. It is well understood that established deraining methods are derived based on one specific imaging model, neglecting the underlying correlations between different weather models and thereby limiting the applicability of these standard methods in real scenarios. To ameliorate this issue, in this work, we first explore the inherent relationship between a rain model and the haze one established up to date. We discover that these two models experience similar degradations in the low-frequency components (i.e., similarity) but diverse degradations in the high-frequency areas (i.e., diversity). Based on these observations, we develop a Similarity-Diversity model to describe these characteristics. Afterwards, we introduce a novel deep neural network to restore the rain-free background embedding the similarity-diversity model, namely deep similarity-diversity network (DSDNet). Extensive experiments have been conducted to evaluate our proposed method that outperforms the other state of the art deraining techniques. On the other hand, we deploy the proposed algorithm with Google Vision API for object recognition, which also obtains satisfactory results both qualitatively and quantitatively.
- 5 November 2023
- Published by Springer Nature
- p. 93-105
Discriminative Region Enhancing and Suppression Network for Fine-Grained Visual Categorization
- 5 November 2023
- Published by Springer Nature
- p. 93-105
Discriminative Region Enhancing and Suppression Network for Fine-Grained Visual Categorization
- 5 November 2023
- Published by Springer Nature
- p. 185-198
Feature Channel Adaptive Enhancement for Fine-Grained Visual Classification
- 5 November 2023
- Published by Springer Nature
- p. 185-198
Feature Channel Adaptive Enhancement for Fine-Grained Visual Classification
- 5 November 2023
- Published by Springer Nature
- p. 279-292
Multi-discriminative Parts Mining for Fine-Grained Visual Classification
- 5 November 2023
- Published by Springer Nature
- p. 279-292
Multi-discriminative Parts Mining for Fine-Grained Visual Classification
- 14 December 2022
- Published by Springer Nature
- p. 202-210
Cross-Layer Feature Attention Module for Multi-scale Object Detection
- 14 December 2022
- Published by Springer Nature
- p. 202-210
Cross-Layer Feature Attention Module for Multi-scale Object Detection
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Cascading and Residual Connected Network for Single Image Superresolution
Convolution neural networks facilitate the significant process of single image super‐resolution (SISR). However, most of the existing CNN‐based models suffer from numerous parameters and excessively deeper structures. Moreover, these models relying on in‐depth features commonly ignore the hints of low‐level features, resulting in poor performance. This paper demonstrates an intriguing network for SISR with cascading and residual connections (CASR), which alleviates these problems by extracting features in a small net called head module via the strategies based on the depthwise separable convolution and deformable convolution. Moreover, we also include a cascading residual block (CAS‐Block) for the upsampling process, which benefits the gradient propagation and feature learning while easing the model training. Extensive experiments conducted on four benchmark datasets demonstrate that the proposed method is superior to the latest SISR methods in terms of quantitative indicators and realistic visual effects.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessCascading and Residual Connected Network for Single Image Superresolution
Convolution neural networks facilitate the significant process of single image super‐resolution (SISR). However, most of the existing CNN‐based models suffer from numerous parameters and excessively deeper structures. Moreover, these models relying on in‐depth features commonly ignore the hints of low‐level features, resulting in poor performance. This paper demonstrates an intriguing network for SISR with cascading and residual connections (CASR), which alleviates these problems by extracting features in a small net called head module via the strategies based on the depthwise separable convolution and deformable convolution. Moreover, we also include a cascading residual block (CAS‐Block) for the upsampling process, which benefits the gradient propagation and feature learning while easing the model training. Extensive experiments conducted on four benchmark datasets demonstrate that the proposed method is superior to the latest SISR methods in terms of quantitative indicators and realistic visual effects.
- Top Cited PapersOpen Access
- 4 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 51 (3) , 1443-1453
MADNet: A Fast and Lightweight Network for Single-Image Super Resolution
Recently, deep convolutional neural networks (CNNs) have been successfully applied to the single-image super-resolution (SISR) task with great improvement in terms of both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). However, most of the existing CNN-based SR models require high computing power, which considerably limits their real-world applications. In addition, most CNN-based methods rarely explore the intermediate features that are helpful for final image recovery. To address these issues, in this article, we propose a dense lightweight network, called MADNet, for stronger multiscale feature expression and feature correlation learning. Specifically, a residual multiscale module with an attention mechanism (RMAM) is developed to enhance the informative multiscale feature representation ability. Furthermore, we present a dual residual-path block (DRPB) that utilizes the hierarchical features from original low-resolution images. To take advantage of the multilevel features, dense connections are employed among blocks. The comparative results demonstrate the superior performance of our MADNet model while employing considerably fewer multiadds and parameters.
- 4 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 51 (3) , 1443-1453
Top Cited PapersOpen AccessMADNet: A Fast and Lightweight Network for Single-Image Super Resolution
Recently, deep convolutional neural networks (CNNs) have been successfully applied to the single-image super-resolution (SISR) task with great improvement in terms of both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). However, most of the existing CNN-based SR models require high computing power, which considerably limits their real-world applications. In addition, most CNN-based methods rarely explore the intermediate features that are helpful for final image recovery. To address these issues, in this article, we propose a dense lightweight network, called MADNet, for stronger multiscale feature expression and feature correlation learning. Specifically, a residual multiscale module with an attention mechanism (RMAM) is developed to enhance the informative multiscale feature representation ability. Furthermore, we present a dual residual-path block (DRPB) that utilizes the hierarchical features from original low-resolution images. To take advantage of the multilevel features, dense connections are employed among blocks. The comparative results demonstrate the superior performance of our MADNet model while employing considerably fewer multiadds and parameters.