Haichang Yin

Mr. Haichang Yin

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications

1 October 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
HYHaichang Yin
Haichang Yin
KUKin Tak U
Kin Tak U
JWJing Wang
Jing Wang
ZGZhuofan Gan
Zhuofan Gan
With the rapid advancement of image processing techniques, digital image forgery detection has emerged as a critical research area in information forensics. This paper proposes a novel deep learning model based on Multi-view Multi-dimensional Forgery Detection Networks (MMFD-Net), designed to simultaneously determine whether an image has been tampered with and precisely localize the forged regions. By integrating a Multi-stream Edge Feature Learning module with a Multi-dimensional Information Fusion module, MMFD-Net employs joint supervised learning to extract semantics-agnostic forgery features, thereby enhancing both detection performance and model generalization. Extensive experiments demonstrate that MMFD-Net achieves state-of-the-art results on multiple public datasets, excelling in both pixel-level localization and image-level classification tasks, while maintaining robust performance in complex scenarios.

18 September 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JYJianxiong Ye
Jianxiong Ye
ZYZhenghong Yu
Zhenghong Yu
JLJiewu Lin
Jiewu Lin
LLLisheng Lin
Lisheng Lin
HLHongyuan Li
Hongyuan Li
HZhuabing zhou
huabing zhou
Accurately observing the maize tasseling stage is critical for optimizing yield in agricultural ecosystem research. Despite some success in automated observation attempts, automating the tasseling stage remains an open problem. Existing methods lack robustness and fail to meet reliability requirements. To effectively address the heterogeneity in maize growth, this study proposes a new deep learning-based automatic observation method for the maize tasseling stage, named TasselLFANet † . It features a concise and efficient encoder-decoder structure, incorporating a novel Receptive Field Synthesis (RFS) module to enhance the encoder’s responsiveness to semantic information, and a pair of parameter operators to improve task adaptability in the decoder’s upsampled features. Furthermore, the close intertwining of leaves and tassels during the tasseling stage results in frequent occlusion. We made an important observation that simulated occlusion learning with contextual information is highly effective. Therefore we propose a clever image enhancement method called Accurate-Context occlusion, which is a simple copy-paste process but fully considers the contextual information in the image. To assess the effectiveness of the proposed method, we curated an open cross-domain Maize Tasseling Stage (MTS) dataset, encompassing 7 image series of continuous 4-year sequences. Extensive experiments demonstrate that TasselLFANet † achieves exceptional performance and outstanding accuracy in automatic tasseling stage observation, with a detection accuracy AP 50 of 0.935 and a counting error MAE of 1.18, markedly surpassing advanced computer vision methods. This establishes it as an effective automated observation method for the maize tasseling stage, providing a highly secure alternative to manual observations.

16 July 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
HYHaichang Yin
Haichang Yin
KUKin Tak U
Kin Tak U
JWJing Wang
Jing Wang
WMWuyue Ma
Wuyue Ma
Most image forgery localization methods rely on supervised learning, requiring large labeled datasets for training. Recently, several unsupervised approaches based on the variational autoencoder (VAE) framework have been proposed for forged pixel detection. In these approaches, the latent space is built by a simple Gaussian distribution or a Gaussian Mixture Model. Despite their success, there are still some limitations: (1) A simple Gaussian distribution assumption in the latent space constrains performance due to the diverse distribution of forged images. (2) Gaussian Mixture Models (GMMs) introduce non-convex log-sum-exp functions in the Kullback–Leibler (KL) divergence term, leading to gradient instability and convergence issues during training. (3) Estimating GMM mixing coefficients typically involves either the expectation-maximization (EM) algorithm before VAE training or a multilayer perceptron (MLP), both of which increase computational complexity. To address these limitations, we propose the Deep ViT-VAE-GMM (DVVG) framework. First, we employ Jensen’s inequality to simplify the KL divergence computation, reducing gradient instability and improving training stability. Second, we introduce convolutional neural networks (CNNs) to adaptively estimate the mixing coefficients, enabling an end-to-end architecture while significantly lowering computational costs. Experimental results on benchmark datasets demonstrate that DVVG not only enhances VAE performance but also improves efficiency in modeling complex latent distributions. Our method effectively balances performance and computational feasibility, making it a practical solution for real-world image forgery localization.

19 July 2024
Verified
Conference Paper
Open access
YXYan Xiang
Yan Xiang
HYHaichang Yin
Haichang Yin
This paper introduces PCGA-Net, an advanced end-to-end network design for precise image forgery localization (IFL). To accurately detect tampered regions, PCGA-Net employs a Progressive Cascaded Group Attention Module (CGAM) at the pixel level. The CGAM module enhances tampering clue identification by dividing RGB features into sub-features and cascading attention maps for each head. A Parallel Convolution (PC) Block refines crucial texture information, boosting computational efficiency and cross-channel tampering detection. Using the lightweight HRNet as its backbone, PCGA-Net encodes RGB features to provide a robust multi-scale global representation. The Decoder, equipped with multiple CGAMs, progressively reconstructs accurate prediction masks. Extensive empirical evaluations on various datasets confirm the superior performance of PCGA-Net in localizing forgeries, establishing its innovative advantage in the field.