YTYichun Tai

Yichun Tai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yichun Tai has a total of 21 co-authors. Here are the top co-authors by number of shared publications:

  • Zhijiang Zhang

    School of Communication and Information Engineering, Shanghai University, Shanghai, China

    9 shared publications
  • Tao Peng

    Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, 99 Shangda Road, Shanghai 200444, China

    3 shared publications
  • Liang Yu

    Shanghai Aircraft Design and Research Institute, Shanghai, People’s Republic of China

    2 shared publications
  • Wenhui Chen

    School of Communication and Information Engineering Shanghai University PR China

    2 shared publications
  • Zhenzhen Huang

    School of Communication and Information Engineering, Shanghai University, Shanghai, China

    2 shared publications
  • Dan Zeng

    School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and The Technology Innovation Center for Collaborative Applications of Natural Resources Data in GBA, MNR, Guangzhou, China

    1 shared publication

Latest Publications

  • Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition

    by Yichun Tai, Kun Yang, Tao Peng, Zhenzhen Huang, Zhijiang Zhang

    The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge the dataset by generating samples with generative models. However, their generation quality is still limited by the insufficiency of defect image samples. To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation. To tackle with the distinctive distribution gap between steel surface images and generated images of the diffusion model, we propose two processes. First, we align the distribution by adapting parameters of the diffusion model, adopted both in the token embedding space and network parameter space. Besides, in the generation process, we propose image-oriented generation rather than from pure Gaussian noises. We conduct extensive experiments on steel surface defect dataset, demonstrating state-of-the-art performance on generating high-quality samples and training recognition models, and both designed processes are significant for the performance. Note to Practitioners —This article introduces StableSDG, a method that generates realistic defect images even with limited data. It overcomes the shortcomings of current deep learning approaches that need large datasets to train from scratch. Our solution is to adapt a text-to-image diffusion model for defect generation. The proposed strategy involves two processes: training to adapt token embeddings and model parameters, and generation from partially perturbed defect images. The results show enhanced generation quality and improved accuracy for recognition models trained on the expanded dataset. StableSDG can be practically applied to efficiently enlarge a defect dataset, even when starting with a small amount of data.


  • Open Access

    Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition

    by Yichun Tai, Kun Yang, Tao Peng, Zhenzhen Huang, Zhijiang Zhang

    The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge the dataset by generating samples with generative models. However, their generation quality is still limited by the insufficiency of defect image samples. To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation. To tackle with the distinctive distribution gap between steel surface images and generated images of the diffusion model, we propose two processes. First, we align the distribution by adapting parameters of the diffusion model, adopted both in the token embedding space and network parameter space. Besides, in the generation process, we propose image-oriented generation rather than from pure Gaussian noises. We conduct extensive experiments on steel surface defect dataset, demonstrating state-of-the-art performance on generating high-quality samples and training recognition models, and both designed processes are significant for the performance.


  • Open Access

    Ellipse Detection with Applications of Convolutional Neural Network in Industrial Images

    by Kang Liu, Yonggang Lu, Rubing Bai, Kun Xu, Tao Peng, Yichun Tai, Zhijiang Zhang

    Ellipse detection has a very wide range of applications in the field of industrial production, especially in the geometric detection of metallurgical hinge pins. However, the factors in industrial images, such as small object size and incomplete ellipse in the image boundary, bring challenges to ellipse detection, which cannot be solved by existing methods. This paper proposes a method for ellipse detection in industrial images, which utilizes the extended proposal operation to prevent the loss of ellipse rotation angle features during ellipse regression. Moreover, the Gaussian angle distance conforming to the ellipse axioms is adopted and combined with smooth L1 loss as the ellipse regression loss function to enhance the prediction accuracy of the ellipse rotation angle. The effectiveness of the proposed method is demonstrated on the hinge pins dataset, with experiment results showing an AP* of 80.93% and indicating superior detection performance compared to other methods. It is thus suitable for engineering applications and can provide visual guidance for the precise measurement of ellipse-like mechanical parts.


  • Open Access

    Multi-Agent Semi-Siamese Training for Long-Tail and Shallow Face Learning

    by Yichun Tai, Hailin Shi, Dan Zeng, Hang Du, Yibo Hu, Zicheng Zhang, Zhijiang Zhang, Tao Mei

    With the recent development of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in various applications. However, unlike the existing public face datasets, in many real-world scenarios of face recognition, the depth of the training dataset is shallow, which means that only two face images are available for each ID. With the non-uniform increase of samples, such issue is converted to a more general case, known as long-tail face learning, which suffers from data imbalance and intra-class diversity dearth simultaneously. These adverse conditions damage the training and result in the decline of model performance. Based on Semi-Siamese Training, we introduce an advanced solution, namedMulti-Agent Semi-Siamese Training(MASST), to address these problems. MASST includes a probe network and multiple gallery agents—the former aims to encode the probe features, and the latter constitutes a stack of networks that encode the prototypes (gallery features). For each training iteration, the gallery network, which is sequentially rotated from the stack, and the probe network form a pair of Semi-Siamese networks. We give the theoretical and empirical analysis that, given the long-tail (or shallow) data and training loss, MASST smooths the loss landscape and satisfies the Lipschitz continuity with the help of multiple agents and the updating gallery queue. The proposed method is out of extra-dependency, and thus can be easily integrated with the existing loss functions and network architectures. It is worth noting that although multiple gallery agents are employed for training, only the probe network is needed for inference, without increasing the inference cost. Extensive experiments and comparisons demonstrate the advantages of MASST for long-tail and shallow face learning.


  • Open Access

    BARS: A Benchmark for Airport Runway Segmentation

    by Wenhui Chen, Zhijiang Zhang, Liang Yu, Yichun Tai

    Airport runway segmentation can effectively reduce the accident rate during the landing phase, which has the largest risk of flight accidents. With the rapid development of deep learning (DL), related methods achieve good performance on segmentation tasks and can be well adapted to complex scenes. However, the lack of large-scale, publicly available datasets in this field makes the development of methods based on DL difficult. Therefore, we propose a benchmark for airport runway segmentation, named BARS. Additionally, a semiautomatic annotation pipeline is designed to reduce the annotation workload. BARS has the largest dataset with the richest categories and the only instance annotation in the field. The dataset, which was collected using the X-Plane simulation platform, contains 10,256 images and 30,201 instances with three categories. We evaluate eleven representative instance segmentation methods on BARS and analyze their performance. Based on the characteristic of an airport runway with a regular shape, we propose a plug-and-play smoothing postprocessing module (SPM) and a contour point constraint loss (CPCL) function to smooth segmentation results for mask-based and contour-based methods, respectively. Furthermore, a novel evaluation metric named average smoothness (AS) is developed to measure smoothness. The experiments show that existing instance segmentation methods can achieve prediction results with good performance on BARS. SPM and CPCL can effectively enhance the AS metric while modestly improving accuracy. Our work will be available at https://github.com/c-wenhui/BARS.

  • BARS: a benchmark for airport runway segmentation

    by Wenhui Chen, Zhijiang Zhang, Liang Yu, Yichun Tai


  • Open Access

    Local Feature Extraction Network for Point Cloud Analysis

    by Zehao Zhou, Yichun Tai, Jianlin Chen, Zhijiang Zhang

    Geometric feature extraction of 3D point clouds plays an important role in many 3D computer vision applications such as region labeling, 3D reconstruction, object segmentation, and recognition. However, hand-designed features on point clouds lack semantic information, so cannot meet these requirements. In this paper, we propose local feature extraction network (LFE-Net) which focus on extracting local feature for point clouds analysis. Such geometric features learning from a relation of local points can be used in a variety of shape analysis problems such as classification, part segmentation, and point matching. LFE-Net consists of local geometric relation (LGR) module which aims to learn a high-dimensional local feature to express the relation between points and their neighbors. Benefiting from the additional singular values of local points and hierarchical neural networks, the learned local features are robust to permutation and rigid transformation so that they can be transformed into 3D descriptors. Moreover, we embed prior spatial information of the local points into the sub-features for combining features from multiple levels. LFE-Net achieves state-of-the-art performances on standard benchmarks including ModelNet40, ShapeNetPart.