arXiv subjects

Chengyu Zhou

Publications and source records attributed to Chengyu Zhou.

7 recordsLinked to original sources

arXiv2026

Monad Structures on Topological Spaces Comprising Mislove's Random Variables

Mislove, Goubault and Varacca investigated how to define random variables in Domain theory to form monads over the category of bounded complete domains. They intended to model probabilistic programming languages with their random variables monads. In this paper, we focus on the random variables defined by Mislove from a topological perspective. We provide a topology for $\surd$-max continuous random variables on a $T_0$ space, we construct a new $T_0$ space, where $\surd$-max property is essential for the monad structures. We show that the spaces of normalized $\surd$-max simple random variables form a monad over the category of $T_0$ spaces and that the spaces of normalized $\surd$-max continuous random variables give a monad over the category of d-spaces. In addition, on a sober space, the space of normalized $\surd$-max continuous random variables is the sobrification of the space of normalized $\surd$-max simple random variables.

cs.LO↗

arXiv2025

All-optical discrete illumination-based compressed ultrafast photography

Snapshot ultrafast optical imaging (SUOI) plays a vital role in capturing complex transient events in real time, with significant implications for both fundamental science and practical applications. As an outstanding talent in SUOI, compressed ultrafast photography (CUP) has demonstrated remarkable frame rate reaching trillions of frames per second and hundreds of sequence depth. Nevertheless, as CUP relies on streak cameras, the system's imaging fidelity suffers from an inevitable limitation induced by the charge coupling artifacts in a streak camera. Moreover, although advanced image reconstruction algorithms have improved the recovered scenes, its high compression ratio still causes a compromise in image quality. To address these challenges, we propose a novel approach termed all-optical discrete illumination compressed ultrafast photography (AOD-CUP), which employs a free-space angular-chirp-enhanced delay (FACED) technique to temporally stretch femtosecond pulses and achieves discrete illumination for dynamic scenes. With its distinctive system architecture, AOD-CUP features adjustable frame numbers and flexible inter-frame intervals ranging from picoseconds to nanoseconds, thereby achieving high-fidelity ultrafast imaging in a snapshot. Experimental results demonstrate the system's superior dynamic spatial resolution and its capability to visualize ultrafast phenomena with complex spatial details, such as stress wave propagation in LiF crystals and air plasma channel formation. These results highlight the potential of AOD-CUP for high-fidelity, real-time ultrafast imaging, which provides an unprecedented tool for advancing the frontiers of ultrafast science.

physics.optics↗

arXiv2025

Some Consistent Power Constructions

Consistent Hoare, Smyth and Plotkin power domains are introduced and discussed by Yuan and Kou. The consistent algebraic operation $+$ defined by them is a binary partial Scott continuous operation satisfying the requirement: $a+b$ exists whenever there exists a $c$ which is greater than $a$ and $b$. We extend the consistency to be a categorical concept and obtain an approach to generating consistent monads from monads on dcpos whose images equipped with some algebraic operations. Then we provide two new power constructions over domains: the consistent Plotkin index power domain and the consistent probabilistic power domain. Moreover, we verify these power constructions are free.

cs.LO↗

arXiv2024

Federated Multilinear Principal Component Analysis with Applications in Prognostics

Multilinear Principal Component Analysis (MPCA) is a widely utilized method for the dimension reduction of tensor data. However, the integration of MPCA into federated learning remains unexplored in existing research. To tackle this gap, this article proposes a Federated Multilinear Principal Component Analysis (FMPCA) method, which enables multiple users to collaboratively reduce the dimension of their tensor data while keeping each user's data local and confidential. The proposed FMPCA method is guaranteed to have the same performance as traditional MPCA. An application of the proposed FMPCA in industrial prognostics is also demonstrated. Simulated data and a real-world data set are used to validate the performance of the proposed method.

cs.LG↗

arXiv2023

Supervised Contrastive Learning for Fine-grained Chromosome Recognition

Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity and intra-class variation of chromosomes. To address this issue, we propose a supervised contrastive learning strategy that is tailored to train model-agnostic deep networks for reliable chromosome classification. This method enables extracting fine-grained chromosomal embeddings in latent space. These embeddings effectively expand inter-class boundaries and reduce intra-class variations, enhancing their distinctiveness in predicting chromosome types. On top of two large-scale chromosome datasets, we comprehensively validate the power of our contrastive learning strategy in boosting cutting-edge deep networks such as Transformers and ResNets. Extensive results demonstrate that it can significantly improve models' generalization performance, with an accuracy improvement up to +4.5%. Codes and pretrained models will be released upon acceptance of this work.

cs.CV↗

arXiv2023

A Supervised Tensor Dimension Reduction-Based Prognostics Model for Applications with Incomplete Imaging Data

This paper proposes a supervised dimension reduction methodology for tensor data which has two advantages over most image-based prognostic models. First, the model does not require tensor data to be complete which expands its application to incomplete data. Second, it utilizes time-to-failure (TTF) to supervise the extraction of low-dimensional features which makes the extracted features more effective for the subsequent prognostic. Besides, an optimization algorithm is proposed for parameter estimation and closed-form solutions are derived under certain distributions.

cs.LG↗

arXiv2023

Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers. Meanwhile, most deep learning models are known to be vulnerable to adversarial examples that are crafted with small perturbations but could mislead the model prediction. In this work, we observe that the robustness on the MOT trackers is rarely studied, and it is challenging to attack the MOT system since its mature association algorithms are designed to be robust against errors during the tracking. To this end, we analyze the vulnerability of popular MOT trackers and propose a novel adversarial attack method called Tracklet-Switch (TraSw) against the complete tracking pipeline of MOT. The proposed TraSw can fool the advanced deep pedestrian trackers (i.e., FairMOT and ByteTrack), causing them fail to track the targets in the subsequent frames by perturbing very few frames. Experiments on the MOT-Challenge datasets (i.e., 2DMOT15, MOT17, and MOT20) show that TraSw can achieve an extraordinarily high success attack rate of over 95% by attacking only four frames on average. To our knowledge, this is the first work on the adversarial attack against the pedestrian MOT trackers. Code is available at https://github.com/JHL-HUST/TraSw .

cs.CV↗