Shengchuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shengchuan Zhang has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Liujuan Cao
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China
12 shared publications - Rongrong Ji
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
7 shared publications - Yansong Qu
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
5 shared publications - Jianghang Lin
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China
4 shared publications Liujuan Cao
Xiamen University
4 shared publications- Xinyang Li
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16239-16248
LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16239-16248
Open AccessLASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13357-13365
GFR-SAM: Training-Free Referring Camouflaged Object Segmentation via Cross-Image Prompting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13357-13365
Open AccessGFR-SAM: Training-Free Referring Camouflaged Object Segmentation via Cross-Image Prompting
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11259-11268
Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11259-11268
Open AccessGenerate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2841-2850
What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2841-2850
Open AccessWhat You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3673-3682
Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3673-3682
Open AccessTraining-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9444-9453
SynergyAmodal: Deocclude Anything with Text Control
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9444-9453
Open AccessSynergyAmodal: Deocclude Anything with Text Control
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessDrag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
- Open Access
UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.
Open AccessUCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.
- Open Access
- 30 December 2024
- Published by MDPI AG in Mathematics
- Vol. 13 (1) , 108
Probabilistic Automated Model Compression via Representation Mutual Information Optimization
Deep neural networks, despite their remarkable success in computer vision tasks, often face deployment challenges due to high computational demands and memory usage. Addressing this, we introduce a probabilistic framework for automated model compression (Prob-AMC) that optimizes pruning, quantization, and knowledge distillation simultaneously using information theory. Our approach is grounded in maximizing the mutual information between the original and compressed network representations, ensuring the preservation of essential features under resource constraints. Specifically, we employ layer-wise self-representation mutual information analysis, sampling-based pruning and quantization allocation, and progressive knowledge distillation using the optimal compressed model as a teacher assistant. Through extensive experiments on CIFAR-10 and ImageNet, we demonstrate that Prob-AMC achieves a superior compression ratio of 33.41× on ResNet-18 with only a 1.01% performance degradation, outperforming state-of-the-art methods in terms of both compression efficiency and accuracy. This optimization process is highly practical, requiring merely a few GPU hours, and bridges the gap between theoretical information measures and practical model compression, offering significant insights for efficient deep learning deployment.
- 30 December 2024
- Published by MDPI AG in Mathematics
- Vol. 13 (1) , 108
Open AccessProbabilistic Automated Model Compression via Representation Mutual Information Optimization
Deep neural networks, despite their remarkable success in computer vision tasks, often face deployment challenges due to high computational demands and memory usage. Addressing this, we introduce a probabilistic framework for automated model compression (Prob-AMC) that optimizes pruning, quantization, and knowledge distillation simultaneously using information theory. Our approach is grounded in maximizing the mutual information between the original and compressed network representations, ensuring the preservation of essential features under resource constraints. Specifically, we employ layer-wise self-representation mutual information analysis, sampling-based pruning and quantization allocation, and progressive knowledge distillation using the optimal compressed model as a teacher assistant. Through extensive experiments on CIFAR-10 and ImageNet, we demonstrate that Prob-AMC achieves a superior compression ratio of 33.41× on ResNet-18 with only a 1.01% performance degradation, outperforming state-of-the-art methods in terms of both compression efficiency and accuracy. This optimization process is highly practical, requiring merely a few GPU hours, and bridges the gap between theoretical information measures and practical model compression, offering significant insights for efficient deep learning deployment.