Zhaofeng Niu

Ms. Zhaofeng Niu

Nara Institute of Science and Technology
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
19 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Zhaofeng NiuZhaofeng Niu
Zhaofeng Niu
YFYuichiro Fujimoto
Yuichiro Fujimoto
MKMasayuki Kanbara
Masayuki Kanbara
TSTaishi Sawabe
Taishi Sawabe
HKHirokazu Kato
Hirokazu Kato
The truncated signed distance function (TSDF) fusion is one of the key operations in the 3D reconstruction process. However, existing TSDF fusion methods usually suffer from the inevitable sensor noises. In this paper, we propose a new TSDF fusion network, named DFusion, to minimize the influences from the two most common sensor noises, i.e., depth noises and pose noises. To the best of our knowledge, this is the first depth fusion for resolving both depth noises and pose noises. DFusion consists of a fusion module, which fuses depth maps together and generates a TSDF volume, as well as the following denoising module, which takes the TSDF volume as the input and removes both depth noises and pose noises. To utilize the 3D structural information of the TSDF volume, 3D convolutional layers are used in the encoder and decoder parts of the denoising module. In addition, a specially-designed loss function is adopted to improve the fusion performance in object and surface regions. The experiments are conducted on a synthetic dataset as well as a real-scene dataset. The results prove that our method outperforms existing methods.

10 April 2025 in Sensors
Verified
Journal Article
Open access
PDF file
XCXingfu Cheng
Xingfu Cheng
Zhaofeng NiuZhaofeng Niu
Zhaofeng Niu
ZJZhouqiang Jiang
Zhouqiang Jiang
LLLiangzhi Li
Liangzhi Li
Deep neural networks (DNNs) have demonstrated exceptional performance in image classification. However, their “black-box” nature raises concerns about trust and transparency, particularly in high-stakes fields such as healthcare and autonomous systems. While explainable AI (XAI) methods attempt to address these concerns through feature- or concept-based explanations, existing approaches are often limited by the need for manually defined concepts, overly abstract granularity, or misalignment with human semantics. This paper introduces the Enhanced Bottleneck Concept Learner (E-BotCL), a self-supervised framework that autonomously discovers task-relevant, interpretable semantic concepts via a dual-path contrastive learning strategy and multi-task regularization. By combining contrastive learning to build robust concept prototypes, attention mechanisms for spatial localization, and feature aggregation to activate concepts, E-BotCL enables end-to-end concept learning and classification without requiring human supervision. Experiments conducted on the CUB200 and ImageNet datasets demonstrated that E-BotCL significantly enhanced interpretability while maintaining classification accuracy. Specifically, two interpretability metrics, the Concept Discovery Rate (CDR) and Concept Consistency (CC), improved by 0.6104 and 0.4486, respectively. This work advances the balance between model performance and transparency, offering a scalable solution for interpretable decision-making in complex vision tasks.

8 June 2025
Verified
Book Chapter
Closed access
PDF file
Zhaofeng NiuZhaofeng Niu
Zhaofeng Niu
LWLihua Wang
Lihua Wang
ZJZhouqiang Jiang
Zhouqiang Jiang
BWBowen Wang
Bowen Wang
GLGuang-Shun Li
Guang-Shun Li
LLLiangzhi Li
Liangzhi Li

24 May 2024
Verified
Conference Paper
Open access
CSChuanguo Shen
Chuanguo Shen
Zhaofeng NiuZhaofeng Niu
Zhaofeng Niu
BWBowen Wang
Bowen Wang
GLGuang-Shun Li
Guang-Shun Li
LLLiangzhi Li
Liangzhi Li
The development of the highly observed field of semantic segmentation is hindered by time-consuming and complex manual mask annotations. This study seeks to address this issue by introducing a new method, WSSS-DM, which allows end-to-end weakly supervised semantic segmentation based solely on text descriptions. Using the cross attention word-pixel scores derived from the denoising self-network of the diffusion model, masks are generated. Different masks collected after screening are then combined onto the same image, forming an image-label pairs corresponding to the original image. Simultaneously, we categorize based on the quality of labels, differentiating the degree to which explainable features of images can be accurately obtained. In the experiments performed on the COCO captions dataset, the high-quality category yielded an mIoU of 37.4 and an mAcc of 42.17, thereby substantiating the effectiveness of our method.

24 May 2024
Verified
Conference Paper
Open access
LWLihua Wang
Lihua Wang
Zhaofeng NiuZhaofeng Niu
Zhaofeng Niu
BWBowen Wang
Bowen Wang
GLGuang-Shun Li
Guang-Shun Li
LLLiangzhi Li
Liangzhi Li
Transformers have made substantial contributions to various computer vision tasks, leveraging their attention mechanisms. However, their performance tends to be deficient on small-scale datasets. This shortfall primarily arises because Transformers lack the inherent inductive bias that forms a cornerstone of Convolutional Neural Networks (CNNs). To address this, we propose an innovative model called ConTransNet, which encapsulates a Convolution-Transformer synergy for enhanced learning in data-limited environments. A trained CNN is used to impart feature knowledge to a Transformer, which significantly enhances the Transformer's performance. Our strategy includes a unique positional localization technique designed for optimal feature transfer. Compared to pure Transformer models, our method increased mIoU by 10.3% on the half Cityscapes dataset. This finding highlights our method's effectiveness in enhancing Transformer performance on small-scale datasets and point towards potential advancements through blending CNNs and Transformers for such scenarios.