Yixiong Liang, Yuan Mao, Jiazhi Xia, Yao Xiang, Jianfeng Liu
In this paper, we present a fast yet effective method for pixel-level scale-invariant image fusion in spatial domain based on the scale-space theory. Specifically, we propose a scale-invariant structure saliency selection scheme based on the difference-of-Gaussian (DoG) pyramid of images to build the weights or activity map. Due to the scale-invariant structure saliency selection, our method can keep both details of small size objects and the integrity information of large size objects in images. In addition, our method is very efficient since there are no complex operation involved and easy to be implemented and therefore can be used for fast high resolution images fusion. Experimental results demonstrate the proposed method yields competitive or even better results comparing to state-of-the-art image fusion methods both in terms of visual quality and objective evaluation metrics. Furthermore, the proposed method is very fast and can be used to fuse the high resolution images in real-time. Code is available at https://github.com/yiqingmy/Fusion.
Mao Yuan, Weiwei Zhu, Haiyan Zhang, Shijie Huang, Mengyao Xue, Di Li, Youling Yue, Pei Wang, 1 Jiarui Niu, Yuxuan Hu, Chunjiang Li, Chenchen Miao, Yu Wang, Lingqi Meng, Bo Peng
May 18, 2022·astro-ph.IM·PDF Radio frequency interference (RFI) is a significant challenge faced by today's radio astronomers. While most past efforts were devoted to cleaning the RFI from the data, we develop a novel method for categorizing and cataloguing RFI for forensic purpose. We present a classifier that categorizes RFI into different types based on features extracted using Principal Component Analysis (PCA) and Fourier analysis. The classifier can identify narrowband non-periodic RFI above 2 sigma, narrowband periodic RFI above 3 sigma, and wideband impulsive RFI above 5 sigma with F1 scores between 0.87 and 0.91 in simulation. This classifier could be used to identify the sources of RFI as well as to clean RFI contamination (particularly in pulsar search). In the long-term analysis of the categorized RFI, we found a special type of drifting periodic RFI that is detrimental to pulsar search. We also found evidences of an increased rate of impulsive RFI when the telescope is pointing toward the cities. These results demonstrate this classifier's potential as a forensic tool for RFI environment monitoring of radio telescopes.
Yuan Ma, Jiankang Wei, Yilun Lyu, Kehao Chen, Jingtong Huang
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific triggers into the training data, causing the model to produce targeted incorrect outputs in the presence of the corresponding triggers. More sophisticated attacks modify the model's architecture directly, embedding backdoors that are harder to detect as they evade traditional data-based detection methods. However, the drawback of the architectural modification based backdoor attacks is that the trigger must be visible in order to activate the backdoor. To further strengthen the invisibility of the backdoor attacks, a novel backdoor attack method is presented in the paper. To be more specific, this method embeds the backdoor within the model's architecture and has the capability to generate inconspicuous and stealthy triggers. The attack is implemented by modifying pre-trained models, which are then redistributed, thereby posing a potential threat to unsuspecting users. Comprehensive experiments conducted on standard computer vision benchmarks validate the effectiveness of this attack and highlight the stealthiness of its triggers, which remain undetectable through both manual visual inspection and advanced detection tools.
Kewen Liu, Yuan Ma, Hongxia Xiong, Zejun Yan, Zhijun Zhou, Panpan Fang, Chaoyang Liu
In order to address the issue that medical image would suffer from severe blurring caused by the lack of high-frequency details in the process of image super-resolution reconstruction, a novel medical image super-resolution method based on dense neural network and blended attention mechanism is proposed. The proposed method adds blended attention blocks to dense neural network(DenseNet), so that the neural network can concentrate more attention to the regions and channels with sufficient high-frequency details. Batch normalization layers are removed to avoid loss of high-frequency texture details. Final obtained high resolution medical image are obtained using deconvolutional layers at the very end of the network as up-sampling operators. Experimental results show that the proposed method has an improvement of 0.05db to 11.25dB and 0.6% to 14.04% on the peak signal-to-noise ratio(PSNR) metric and structural similarity index(SSIM) metric, respectively, compared with the mainstream image super-resolution methods. This work provides a new idea for theoretical studies of medical image super-resolution reconstruction.
Yuan Ma, Junlin Hou, Chao Zhang, Yukun Zhou, Zongyuan Ge, Haoran Xie, Lie Ju
Learning from noisy labels remains a major challenge in medical image analysis, where annotation demands expert knowledge and substantial inter-observer variability often leads to inconsistent or erroneous labels. Despite extensive research on learning with noisy labels (LNL), the robustness of existing methods in medical imaging has not been systematically assessed. To address this gap, we introduce LNMBench, a comprehensive benchmark for Label Noise in Medical imaging. LNMBench encompasses \textbf{10} representative methods evaluated across 7 datasets, 6 imaging modalities, and 3 noise patterns, establishing a unified and reproducible framework for robustness evaluation under realistic conditions. Comprehensive experiments reveal that the performance of existing LNL methods degrades substantially under high and real-world noise, highlighting the persistent challenges of class imbalance and domain variability in medical data. Motivated by these findings, we further propose a simple yet effective improvement to enhance model robustness under such conditions. The LNMBench codebase is publicly released to facilitate standardized evaluation, promote reproducible research, and provide practical insights for developing noise-resilient algorithms in both research and real-world medical applications.The codebase is publicly available on https://github.com/myyy777/LNMBench.
Yixiong Liang, Yuan Mao, Zhihong Tang, Meng Yan, Yuqian Zhao, Jianfeng Liu
In this paper we propose a very efficient method to fuse the unregistered multi-focus microscopical images based on the speed-up robust features (SURF). Our method follows the pipeline of first registration and then fusion. However, instead of treating the registration and fusion as two completely independent stage, we propose to reuse the determinant of the approximate Hessian generated in SURF detection stage as the corresponding salient response for the final image fusion, thus it enables nearly cost-free saliency map generation. In addition, due to the adoption of SURF scale space representation, our method can generate scale-invariant saliency map which is desired for scale-invariant image fusion. We present an extensive evaluation on the dataset consisting of several groups of unregistered multi-focus 4K ultra HD microscopic images with size of 4112 x 3008. Compared with the state-of-the-art multi-focus image fusion methods, our method is much faster and achieve better results in the visual performance. Our method provides a flexible and efficient way to integrate complementary and redundant information from multiple multi-focus ultra HD unregistered images into a fused image that contains better description than any of the individual input images. Code is available at https://github.com/yiqingmy/JointRF.
Mao Yuan, Weiwei Zhu, Michael Kramer, Bo Peng, Jiguang Lu, Renxin Xu, Lijing Shao, Hong-guang Wang, Lingqi Meng, Jiarui Niu, Rushuang Zhao, Chenchen Miao, Xueli Miao, Mengyao Xue, Yi Feng, Pei Wang, Di Li, Chengmin Zhang, David J. Champion, Emmanuel Fonseca, Huanchen Hu, Jumei Yao, Paulo C. C. Freire, Yanjun Guo
We discover three new weak pulse components in two known pulsars, one in PSR J0304+1932 and two in PSR J1518+4904. These components are emitted about half way between the main emission beam and the interpulse beam (beam from the opposite pole). They are separated from their main pulse peak by $99^{\circ}\pm{3}^{\circ}$ for J0304+1932, $123^{\circ}.6\pm{0^{\circ}.7}$ (leading) and $93^{^{\circ}}\pm 0^{\circ}.4$ (trailing) for J1518+4904, respectively. Their peak-intensity ratios to main pulses are: $\sim$ 0.06% for J0304+1932, $\sim$ 0.17% and $\sim$ 0.83% for J1518+4904. We also analyzed flux fluctuation and profile variation of the emissions for two pulsars. The results show correlations between the weak pulses and their main pulses, indicating that these emissions come from the same pole. We estimated the emission altitude of these weak pulses and derived a height of about half of the pulsar's light-cylinder radius. These pulse components are a unique sample of high-altitude emissions from pulsars, and challenge the current pulsar emission models.
Kewen Liu, Yuan Ma, Hongxia Xiong, Zejun Yan, Zhijun Zhou, Chaoyang Liu, Panpan Fang, Xiaojun Li, Yalei Chen
During training phase, more connections (e.g. channel concatenation in last layer of DenseNet) means more occupied GPU memory and lower GPU utilization, requiring more training time. The increase of training time is also not conducive to launch application of SR algorithms. This's why we abandoned DenseNet as basic network. Futhermore, we abandoned this paper due to its limitation only applied on medical images. Please view our lastest work applied on general images at arXiv:1911.03464.
Yuan Mao, Zheng-Chu Guo
In recent years, functional linear models have attracted growing attention in statistics and machine learning, with the aim of recovering the slope function or its functional predictor. This paper considers online regularized learning algorithm for functional linear models in reproducing kernel Hilbert spaces. Convergence analysis of excess prediction error and estimation error are provided with polynomially decaying step-size and constant step-size, respectively. Fast convergence rates can be derived via a capacity dependent analysis. By introducing an explicit regularization term, we uplift the saturation boundary of unregularized online learning algorithms when the step-size decays polynomially, and establish fast convergence rates of estimation error without capacity assumption. However, it remains an open problem to obtain capacity independent convergence rates for the estimation error of the unregularized online learning algorithm with decaying step-size. It also shows that convergence rates of both prediction error and estimation error with constant step-size are competitive with those in the literature.
Yuan Ma, Kewen Liu, Hongxia Xiong, Panpan Fang, Xiaojun Li, Yalei Chen, Chaoyang Liu
The presence of residual and dense neural networks which greatly promotes the development of image Super-Resolution(SR) have witnessed a lot of impressive results. Depending on our observation, although more layers and connections could always improve performance, the increase of model parameters is not conducive to launch application of SR algorithms. Furthermore, algorithms supervised by L1/L2 loss can achieve considerable performance on traditional metrics such as PSNR and SSIM, yet resulting in blurry and over-smoothed outputs without sufficient high-frequency details, namely low perceptual index(PI). Regarding the issues, this paper develops a perception-oriented single image SR algorithm via dual relativistic average generative adversarial networks. In the generator part, a novel residual channel attention block is proposed to recalibrate significance of specific channels, further increasing feature expression capabilities. Parameters of convolutional layers within each block are shared to expand receptive fields while maintain the amount of tunable parameters unchanged. The feature maps are subsampled using sub-pixel convolution to obtain reconstructed high-resolution images. The discriminator part consists of two relativistic average discriminators that work in pixel domain and feature domain, respectively, fully exploiting the prior that half of data in a mini-batch are fake. Different weighted combinations of perceptual loss and adversarial loss are utilized to supervise the generator to equilibrate perceptual quality and objective results. Experimental results and ablation studies show that our proposed algorithm can rival state-of-the-art SR algorithms, both perceptually(PI-minimization) and objectively(PSNR-maximization) with fewer parameters.
Mao Yuan, Jiguang Lu, Zhiliang Yang, Xiaoyu Lai, Renxin Xu
May 23, 2017·astro-ph.HE·PDF The neutrino burst detected during supernova SN1987A is explained in a strangeon star model, in which it is proposed that a pulsar-like compact object is composed of strangeons (strangeon: an abbreviation of "strange nucleon"). A nascent strangeon star's initial internal energy is calculated, with the inclusion of pion excitation (energy around 10^53 erg, comparable to the gravitational binding energy of a collapsed core). A liquid-solid phase transition at temperature ~ 1-2 MeV may occur only a few ten-seconds after core-collapse, and the thermal evolution of strangeon star is then modeled. It is found that the neutrino burst observed from SN 1987A could be re-produced in such a cooling model.
Di Li, Mao Yuan, Lin Wu, Jingye Yan, Xuning Lv, Chao-Wei Tsai, Pei Wang, WeiWei Zhu, Li Deng, Ailan Lan, Renxin Xu, Xianglei Chen, Lingqi Meng, Jian Li, Xiangdong Li, Ping Zhou, Haoran Yang, Mengyao Xue, Jiguang Lu, Chenchen Miao, Weiyang Wang, Jiarui Niu, Ziyao Fang, Qiuyang Fu, Yi Feng, Peijin Zhang, Jinchen Jiang, Xueli Miao, Yu Chen, Lingchen Sun, Yang Yang, Xiang Deng, Shi Dai, Xue Chen, Jumei Yao, Yujie Liu, Changheng Li, Minglu Zhang, Yiwen Yang, Yucheng Zhou, Yi-Yi Zhou, Yongkun Zhang, Chenhui Niu, Rushuang Zhao, Lei Zhang, Bo Peng, Ji Wu, Chi Wang
Nov 24, 2024·astro-ph.HE·PDF Long-period radio transients (LPTs) are a newly discovered class of radio emitters with periods ranging from minutes to hours. The astrophysical nature remains undetermined, particularly of LPTs with no detectable companions. We report the first evidence for a plausible supernova remnant (SNR) association with an LPT (DART J1832-0911, 2656.23+-0.15 s period), which supports a neutron star origin of such objects. The dispersion measure of this LPT, SNR's CO emission and HI absorption, and low probability of chance of alignment with field pulsars are all consistent with such an association. The source displays either phase-locked circular or nearly 100\% linear polarization, indicating its strong and geometrically stable magnetic field. No detectable optical counterpart was found, even with a 10m-class telescope. The SNR association and the stable polarization suggest that DART J1832-0911 most likely originates from a young neutron star, whose spin could have been braked by supernova's fallback materials. This discovery provides critical insights into the nature of ultra-long period transients and their link to stellar remnants.
Joe Lemieux, Yuan Ma
Global optimization of the energy consumption of dual power source vehicles such as hybrid electric vehicles, plug-in hybrid electric vehicles, and plug in fuel cell electric vehicles requires knowledge of the complete route characteristics at the beginning of the trip. One of the main characteristics is the vehicle speed profile across the route. The profile will translate directly into energy requirements for a given vehicle. However, the vehicle speed that a given driver chooses will vary from driver to driver and from time to time, and may be slower, equal to, or faster than the average traffic flow. If the specific driver speed profile can be predicted, the energy usage can be optimized across the route chosen. The purpose of this paper is to research the application of Deep Learning techniques to this problem to identify at the beginning of a drive cycle the driver specific vehicle speed profile for an individual driver repeated drive cycle, which can be used in an optimization algorithm to minimize the amount of fossil fuel energy used during the trip.
Mao Yuan, Jiarui Niu, Yi Feng, Xu-ning Lv, Chenchen Miao, Lingqi Meng, Bo Peng, Li Deng, Jingye Yan, Weiwei Zhu
Fast radio bursts (FRBs) are transient signals exhibiting diverse strengths and emission bandwidths. Traditional single-pulse search techniques are widely employed for FRB detection; yet weak, narrow-band bursts often remain undetectable due to low signal-to-noise ratios (SNR) in integrated profiles. We developed DANCE, a detection tool based on cluster analysis of the original spectrum. It is specifically designed to detect and isolate weak, narrow-band FRBs, providing direct visual identification of their emission properties. This method performs density clustering on reconstructed, RFI-cleaned observational data, enabling the extraction of targeted clusters in time-frequency domain that correspond to the genuine FRB emission range. Our simulations show that DANCE successfully extracts all true signals with SNR~>5 and achieves a detection precision exceeding 93%. Furthermore, through the practical detection of FRB 20201124A, DANCE has demonstrated a significant advantage in finding previously undetectable weak bursts, particularly those with distinct narrow-band features or occurring in proximity to stronger bursts.
Weiwei Zhu, Di Li, Rui Luo, Chenchen Miao, Bing Zhang, Laura Spitler, Duncan Lorimer, Michael Kramer, David Champion, Youling Yue, Andrew Cameron, Marilyn Cruces, Ran Duan, Yi Feng, Jun Han, George Hobbs, Chenhui Niu, Jiarui Niu, Zhichen Pan, Lei Qian, Dai Shi, Ningyu Tang, Pei Wang, Hongfeng Wang, Mao Yuan, Lei Zhang, Xinxin Zhang, Shuyun Cao, Li Feng, Hengqian Gan, Long Gao, Xuedong Gu, Minglei Guo, Qiaoli Hao, Lin Huang, Menglin Huang, Peng Jiang, Chengjin Jin, Hui Li, Qi Li, Qisheng Li, Hongfei Liu, Gaofeng Pan, Bo Peng, Hui Qian, Xiangwei Shi, Jinyuo Song, Liqiang Song, Caihong Sun, Jinghai Sun, Hong Wang, Qiming Wang, Yi Wang, Xiaoyao Xie, Jun Yan, Li Yang, Shimo Yang, Rui Yao, Dongjun Yu, Jinglong Yu, Chengmin Zhang, Haiyan Zhang, Shuxin Zhang, Xiaonian Zheng, Aiying Zhou, Boqin Zhu, Lichun Zhu, Ming Zhu, Wenbai Zhu, Yan Zhu
Apr 29, 2020·astro-ph.HE·PDF We report the discovery of a highly dispersed fast radio burst, FRB~181123, from an analysis of $\sim$1500~hr of drift-scan survey data taken using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The pulse has three distinct emission components, which vary with frequency across our 1.0--1.5~GHz observing band. We measure the peak flux density to be $>0.065$~Jy and the corresponding fluence $>0.2$~Jy~ms. Based on the observed dispersion measure of 1812~cm$^{-3}$~pc, we infer a redshift of $\sim 1.9$. From this, we estimate the peak luminosity and isotropic energy to be $\lesssim 2\times10^{43}$~erg~s$^{-1}$ and $\lesssim 2\times10^{40}$~erg, respectively. With only one FRB from the survey detected so far, our constraints on the event rate are limited. We derive a 95\% confidence lower limit for the event rate of 900 FRBs per day for FRBs with fluences $>0.025$~Jy~ms. We performed follow-up observations of the source with FAST for four hours and have not found a repeated burst. We discuss the implications of this discovery for our understanding of the physical mechanisms of FRBs.
Jin-Chen Jiang, Wei-Yang Wang, Heng Xu, Jiang-Wei Xu, Chun-Feng Zhang, Bo-Jun Wang, De-Jiang Zhou, Yong-Kun Zhang, Jia-Rui Niu, Ke-Jia Lee, Bing Zhang, Jin-Lin Han, Di Li, Wei-Wei Zhu, Zi-Gao Dai, Yi Feng, Wei-Cong Jing, Dong-Zi Li, Rui Luo, Chen-Chen Miao, Chen-Hui Niu, Chao-Wei Tsai, Fa-Yin Wang, Pei Wang, Ren-Xin Xu, Yuan-Pei Yang, Zong-Lin Yang, Ju-Mei Yao, Mao Yuan
As the third paper in the multiple-part series, we report the statistical properties of radio bursts detected from the repeating fast radio burst (FRB) source FRB 20201124A with the Five-hundred-meter Aperture Spherical radio telescope (FAST) during an extremely active episode between the 25th and the 28th of September 2021 (UT). We focus on the polarisation properties of 536 bright bursts with $\mathrm{S/N}>50$. We found that the Faraday rotation measures (RMs) monotonically dropped from $-579 \ {\rm rad \ m^{-2}}$ to $-605 \ {\rm rad \ m^{-2}}$ in the 4-day window. The RM values were compatible with the values ($-300$ to $-900\ {\rm rad \ m^{-2}}$ ) reported 4 month ago (Xu et al. 2022). However, the RM evolution rate in the current observation window was at least an order of magnitude smaller than the one ($\sim 500\ {\rm rad \ m^{-2}\, day^{-1}}$) previously reported during the rapid RM-variation phase, but is still higher than the one ($\le 1\ {\rm rad \ m^{-2} day^{-1}}$ ) during the later RM no-evolution phase. The bursts of FRB 20201124A were highly polarised with the total degree of polarisation (circular plus linear) greater than 90% for more than 90\% of all bursts. The distribution of linear polarisation position angles (PAs), degree of linear polarisation ($L/I$), and degree of circular polarisation ($V/I$) can be characterised with unimodal distribution functions. During the observation window, the distributions became wider with time, i.e. with larger scatter, but the centroids of the distribution functions remained nearly constant. For individual bursts, significant PA variations (confidence level 5-$σ$) were observed in 33% of all bursts. The polarisation of single pulses seems to follow certain complex trajectories on the Poincaré sphere, which may shed light on the radiation mechanism at the source or the plasma properties along the path of FRB propagation.
Shouguo Yang, Zhiqiang Shi, Guodong Zhang, Mingxuan Li, Yuan Ma, Limin Sun
Compiler optimization level recognition can be applied to vulnerability discovery and binary analysis. Due to the exists of many different compilation optimization options, the difference in the contents of the binary file is very complicated. There are thousands of compiler optimization algorithms and multiple different processor architectures, so it is very difficult to manually analyze binary files and recognize its compiler optimization level with rules. This paper first proposes a CNN-based compiler optimization level recognition model: BinEye. The system extracts semantic and structural differences and automatically recognize the compiler optimization levels. The model is designed to be very suitable for binary file processing and is easy to understand. We built a dataset containing 80,028 binary files for the model training and testing. Our proposed model achieves an accuracy of over 97%. At the same time, BinEye is a fully CNN-based system and it has a faster forward calculation speed, at least 8 times faster than the normal RNN-based model. Through our analysis of the model output, we successfully found the difference in assembly codes caused by the different compiler optimization level. This means that the model we proposed is interpretable. Based on our model, we propose a method to analyze the code differences caused by different compiler optimization levels, which has great guiding significance for analyzing closed source compilers and binary security analysis.
Guiyu Zhang, Qunbo Lv, Zui Tao, Baoyu Zhu, Zheng Tan, Yuan Ma
Infrared small target detection plays an important role in the remote sensing fields. Therefore, many detection algorithms have been proposed, in which the infrared patch-tensor (IPT) model has become a mainstream tool due to its excellent performance. However, most IPT-based methods face great challenges, such as inaccurate measure of the tensor low-rankness and poor robustness to complex scenes, which will leadto poor detection performance. In order to solve these problems, this paper proposes a novel double-weighted multi-granularity infrared patch tensor (DWMGIPT) model. First, to capture different granularity information of tensor from multiple modes, a multi-granularity infrared patch tensor (MGIPT) model is constructed by collecting nonoverlapping patches and tensor augmentation based on the tensor train (TT) decomposition. Second, to explore the latent structure of tensor more efficiently, we utilize the auto-weighted mechanism to balance the importance of information at different granularity. Then, the steering kernel (SK) is employed to extract local structure prior, which suppresses background interference such as strong edges and noise. Finally, an efficient optimization algorithm based on the alternating direction method of multipliers (ADMM) is presented to solve the model. Extensive experiments in various challenging scenes show that the proposed algorithm is robust to noise and different scenes. Compared with the other eight state-of-the-art methods, different evaluation metrics demonstrate that our method achieves better detection performance in various complex scenes.
Xiaoge Zhang, Tao Wang, Chao Yan, Fedaa Najdawi, Kai Zhou, Yuan Ma, Yiu-ming Cheung, Bradley A. Malin
Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. To address this issue, we developed TRUECAM, a framework designed to ensure both data and model trustworthiness in non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates 1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs and 2) an ambiguity-guided elimination of tiles to filter out highly ambiguous regions, addressing data trustworthiness, as well as 3) conformal prediction to ensure controlled error rates. We systematically evaluated the framework across multiple large-scale cancer datasets, leveraging both task-specific and foundation models, illustrate that an AI model wrapped with TRUECAM significantly outperforms models that lack such guidance, in terms of classification accuracy, robustness, interpretability, and data efficiency, while also achieving improvements in fairness. These findings highlight TRUECAM as a versatile wrapper framework for digital pathology AI models with diverse architectural designs, promoting their responsible and effective applications in real-world settings.
Kai Zhang, Jingwen Wu, Di Li, Chao-Wei Tsai, Lister Staveley-Smith, Jing Wang, Jian Fu, Travis McIntyre, Mao Yuan, FAST collaboration
The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has started the Commensal Radio Astronomy FasT Survey (CRAFTS). In this paper, we use the technical parameters of FAST derived from commissioning observations to simulate the completeness function for extragalactic HI survey of CRAFTS, HI galaxies from two kinds of mock catalogues are selected. One is generated by Monte-Carlo simulation based on the interpolated mass-velocity width function of the ALFALFA $100\%$ (a.k.a. $α$ .100) catalogue. The other is constructed by semi-analytical N-body simulation based on the $Λ$CDM model. Our results suggest that a two-pass extragalactic HI survey will be able to detect nearly $4.8\times10^{5}$ galaxies, from which the 'faint end' slope of the HI Mass Function (HIMF) can be recovered to $\mathrm{10^{7}\, M_{\odot}}$ and the 'knee mass' of the HIMF can be measured to a redshift of 0.1. Considering the radio frequency interference status and sensitivity limitation, CRAFTS will be efficient in detecting HI galaxies at redshifts below 0.1, which implies a tremendous potential in exploring the galaxy interactions in different environments and the spatial distribution of HI galaxies in the local universe.