Yanbin Peng

Yanbin Peng

Auto-generated profile, based on publicly available information

Yanbin Peng

School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 March 2024 in IEEE Access
Verified
Journal Article
Open access
YPYanbin Peng
Yanbin Peng
ZZZhinian Zhai
Zhinian Zhai
MFMingkun Feng
Mingkun Feng
Existing RGB-D saliency detection models have not fully considered the differences between features at various levels, and lack an effective mechanism for cross-level feature fusion. This article proposes a novel cross-modality cross-level fusion learning framework. The framework mainly contains three modules: Attention Enhancement Module (AEM), Modality Feature Fusion Module (MFM), and Graph Reasoning Module (GRM). AEM is used to enhance the features of the two modalities. MFM is used to integrate the features of the two modalities to achieve cross-modality feature fusion. Subsequently, the modality fusion features are divided into high-level features and low-level features. The high-level features contain the semantic localization information of salient objects, and the low-level features contain the detailed information of salient objects. GRM extends the semantic localization information of salient objects in the high-level features from pixel features to the entire salient object area, thereby achieving cross-level feature fusion. This framework can effectively eliminate background noise and enhance the model’s expressiveness. Extensive experiments were conducted on seven widely used datasets, and the results show that the new method outperforms nine current state-of-the-art RGB-D SOD methods.

18 December 2023 in IEEE Access
Verified
Journal Article
Open access
YPYanbin Peng
Yanbin Peng
MFMingkun Feng
Mingkun Feng
ZZZhijun Zheng
Zhijun Zheng
Salient object detection is a critical task in the field of computer vision. However, existing detection methods still face certain challenges, such as the inability to effectively integrate multimodal features and the blurring of detection result boundaries. To address these issues, this paper proposes a novel RGB-D salient object detection method that combines multimodal feature fusion and contour-guiding techniques. Initially, we employ ResNet50 as the backbone network, and by removing its final pooling layer and fully connected layer, we construct a fully convolutional network specifically for feature extraction from RGB images and depth images. Subsequently, we leverage channel attention mechanism and spatial attention mechanism separately to optimize the RGB image features and depth image features. Following this, we design an interactive feature fusion module to blend the optimized features, thereby obtaining the multimodal fusion features. Furthermore, based on the localization ability of high-level fusion features, we constrain the low-level fusion features, eliminate non-salient objects, and generate salient object contour features. Eventually, we use this contour feature to guide the recognition process of salient objects, resulting in salient objects with clear boundaries. Our approach has been validated across seven RGB-D salient object detection datasets. The experimental results indicate an improvement of 0.21% ~ 1.84% and 0.32% ~ 1.25% respectively in maxF and S metrics, compared to the best competing methods (CMINet, CIR-Net, and CPFP).

13 June 2024 in IEEE Access
Verified
Journal Article
Open access
YPYanbin Peng
Yanbin Peng
MFMingkun Feng
Mingkun Feng
ZZZhinian Zhai
Zhinian Zhai
In the field of Visual Saliency Detection, accurately segmenting salient objects from images is crucial for various applications such as image editing and visual tracking. However, this task becomes particularly challenging due to several issues encountered across different scenes, including (i) the high diversity of salient objects in terms of size, color, and texture; and (ii) the unclear boundaries between salient objects and their backgrounds. To address these challenges, this paper introduces a deep convolutional network based on global guidance map and background attention, named GMBA-Net, for precise segmentation of salient objects. Initially, the Cross-Modal Multi-Scale Attention Module (CMAM) finely integrates information from RGB and depth images. This module employs attention mechanisms to enhance the complementarity between modalities and the expressiveness of multi-scale features, thereby capturing saliency information more effectively at different scales. Following this, the Interactive Global Context Module (IGCM) is utilized to generate a global guidance map, which leverages semantic information from high-level features for accurate localization of salient regions. Finally, a background attention mechanism (BGAM) refines the boundaries of salient objects, significantly improving the clarity of the edges in the saliency maps and achieving precise delineation of salient object boundaries. Experiments conducted on multiple public RGB-D saliency detection datasets have validated the effectiveness of our proposed method. Compared to existing state-of-the-art methods, our model demonstrates significant improvements in terms of saliency detection accuracy and boundary clarity, substantially enhancing the overall performance of saliency detection.

17 March 2025 in IEEE Access
Verified
Journal Article
Open access
ZZZhijun Zheng
Zhijun Zheng
YPYanbin Peng
Yanbin Peng
Accurate salient object detection is of great importance in many computer vision applications. However, due to scale variation and complex backgrounds, achieving effective detection of objects at different scales in various scenes remains a challenging task. To address this, we propose a novel Boundary-Aware Cross-Level Multi-Scale Fusion Network (BCMNet), which enhances salient object detection by fully exploiting cross-level and multi-scale features. Specifically, we propose a Cross-Attention Fusion Module (CAFM) to fuse two modality features, generating modality fusion features. Next, a Boundary-Aware Module (BAM) combines low-level features with high-level features to learn boundary-aware features, which are integrated into each decoding unit during the decoding process. During the decoding stage, a Bidirectional Cross-Level Multi-Scale Module (BCMM) is introduced to effectively integrate cross-level features and perform multi-scale learning. Finally, the output of the BCMM, combined with boundary-aware features, generates saliency prediction maps. We conduct extensive experiments on six datasets, and the experimental results show that, compared to the state-of-the-art methods, the proposed model improves MAE, maxF, maxE, and S metrics by 0~8%, 0~1.34%, 0.11%~0.54%, and 0~0.45%, respectively.

19 August 2024 in IEEE Access
Verified
Journal Article
Open access
YPYanbin Peng
Yanbin Peng
MFMingkun Feng
Mingkun Feng
ZZZhinian Zhai
Zhinian Zhai
ZZZhijun Zheng
Zhijun Zheng
Polyp segmentation is vital for early detection and treatment of colorectal cancer, significantly improving patient prognosis. This paper proposes an efficient and precise polyp segmentation model called the Partial Decoder Localization and Foreground-Background Refinement Network (PDLFBR-Net), which simulates the human object recognition process. Specifically, PDLFBR-Net comprises three key modules: the Cross-level Attention-enhanced Fusion Module (CAFM), the Position Recognition Module (PRM), and the Foreground-Background Refinement Module (FBRM). The CAFM enhances feature representation by fusing information from adjacent levels, providing more discriminative features. The PRM module simulates the human recognition process by using a partial decoder to locate potential polyp tissues from a global perspective. Subsequently, the FBRM is used to perform specific recognition, gradually refining the initial prediction results through foreground and background focusing to achieve precise recognition. Extensive experiments demonstrate that the proposed PDLFBR-Net model significantly outperforms existing state-of-the-art models on five challenging datasets. On the Kvasir-SEG benchmark dataset, the mean Dice and mean IoU values reached 93.7% and 89.5%, respectively, which represents an improvement of 0.4% and 0.6% compared to the best-performing state-of-the-art (SOTA) method.