Author name cluster

Zihao He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2025 Conference Paper

BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution

Zihao He
Shengchuan Zhang
Runze Hu
Yunhang Shen
Yan Zhang

Super-resolution (SR) techniques are critical for enhancing image quality, particularly in scenarios where high-resolution imagery is essential yet limited by hardware constraints. Existing diffusion models for SR have relied predominantly on Gaussian models for noise generation, which often fall short when dealing with the complex and variable texture inherent in natural scenes. To address these deficiencies, we introduce the Bayesian Uncertainty Guided Diffusion Probabilistic Model (BUFF). BUFF distinguishes itself by incorporating a Bayesian network to generate high-resolution uncertainty masks. These masks guide the diffusion process, allowing for the adjustment of noise intensity in a manner that is both context-aware and adaptive. This novel approach not only enhances the fidelity of super-resolved images to their original high-resolution counterparts but also significantly mitigates artifacts and blurring in areas characterized by complex textures and fine details. The model demonstrates exceptional robustness against complex noise patterns and showcases superior adaptability in handling textures and edges within images. Empirical evidence, supported by visual results, illustrates the model's robustness, especially in challenging scenarios, and its effectiveness in addressing common SR issues such as blurring. Experimental evaluations conducted on the DIV2K dataset reveal that BUFF achieves a notable improvement, with a +0.61 increase compared to baseline in SSIM on BSD100, surpassing traditional diffusion approaches by an average additional +0.20dB PSNR gain. These findings underscore the potential of Bayesian methods in enhancing diffusion processes for SR, paving the way for future advancements in the field.

PDF Details DOI

EAAI Journal 2024 Journal Article

An automatic Darknet-based immunohistochemical scoring system for IL-24 in lung cancer

Zihao He
Dongyao Jia
Chuanwang Zhang
Ziqi Li
Nengkai Wu

Immunohistochemical (IHC) detection is of critical importance in the pathological diagnosis of lung cancer. Interleukin-24 (IL-24) is a significant predictive and prognostic marker in IHC detection, which can help to characterize the tumor and predict the clinical course. To determine the score of the IL-24 expression, pathologists will assess the positive area and staining intensity through a microscope and then use a semi-quantitative assessment method to assign a score for each IHC image of lung cancer. However, this process is a time-consuming, imprecise, and subjective process, which can result in inter- and intra-observer discrepancies. Meanwhile, The performance of computer-aided diagnosis (CAD) systems for IHC scoring depends on the quality of manually extracted features. For example, many advanced methods require precise extraction of features of cell nuclei and membranes. However, the complex background and overlapping cells in lung cancer IHC images present significant challenges for segmentation, which can affect the accuracy of the final system's predicted scoring results. In this paper, an automatic Darknet-based IHC scoring system for IL-24 in lung cancer is proposed. Firstly, the original IHC images of lung cancer are blocked and the features are concentrated by a “block attention mechanism, which can reduce the computational burden of the analysis of millions of pixels in IHC images. The blocked images are then inputted into a Darknet-based scoring network, which incorporates a novel feature extraction backbone and loss function to obtain the final scores. To the best of our knowledge, this is the first end-to-end system that directly outputs a clinical score using lung cancer IL-24 IHC images as input. We have constructed a dataset of 5000 manually annotated IL-24 IHC images of lung cancer obtained from the Institute of Life Science and Bioengineering at Beijing Jiaotong University. We will present experimental results to demonstrate the feasibility of our proposed method, which can greatly assist with the clinical diagnosis and treatment of lung cancer.

Details DOI

IJCAI Conference 2019 Conference Paper

Automatic Grassland Degradation Estimation Using Deep Learning

Xiyu Yan
Yong Jiang
Shuai Chen
Zihao He
Chunmei Li
Shu-Tao Xia
Tao Dai
Shuo Dong

Grassland degradation estimation is essential to prevent global land desertification and sandstorms. Typically, the key to such estimation is to measure the coverage of indicator plants. However, traditional methods of estimation rely heavily on human eyes and manual labor, thus inevitably leading to subjective results and high labor costs. In contrast, deep learning-based image segmentation algorithms are potentially capable of automatic assessment of the coverage of indicator plants. Nevertheless, a suitable image dataset comprising grassland images is not publicly available. To this end, we build an original Automatic Grassland Degradation Estimation Dataset (AGDE-Dataset), with a large number of grassland images captured from the wild. Based on AGDE-Dataset, we are able to propose a brand new scheme to automatically estimate grassland degradation, which mainly consists of two components. 1) Semantic segmentation: we design a deep neural network with an improved encoder-decoder structure to implement semantic segmentation of grassland images. In addition, we propose a novel Focal-Hinge Loss to alleviate the class imbalance of semantics in the training stage. 2) Degradation estimation: we provide the estimation of grassland degradation based on the results of semantic segmentation. Experimental results show that the proposed method achieves satisfactory accuracy in grassland degradation estimation.

PDF Details