arXiv subjects

Yanyang Xiao

Publications and source records attributed to Yanyang Xiao.

5 recordsLinked to original sources

arXiv2026

Efficient Computation of Voronoi Diagrams Using Point-in-Cell Tests

Since the Voronoi diagram appears in many applications, the topic of improving its computational efficiency remains attractive. We propose a novel yet efficient method to compute Voronoi diagrams bounded by a given domain, i.e., the clipped or restricted Voronoi diagrams. The intersection of the domain and a Voronoi cell (domain-cell intersection) is generated by removing the part outside the cell from the domain, which can be accomplished by several clippings. Different from the existing methods, we present an edge-based search scheme to find clipping planes (bisectors). A test called point-in-cell is first set up to tell whether a space point is in a target Voronoi cell or not. Then, for each edge of the intermediate domain-cell intersection, we will launch a clipping only if its two endpoints are respectively inside and outside the corresponding Voronoi cell, where the bisector for the clipping can be found by using a few times of point-in-cell tests. Therefore, our method only involves the clippings that contribute to the final results, which is a great advantage over the state-of-the-art methods. Additionally, because each domain-cell intersection can be generated independently, we extend the proposed method to the GPUs for computing Voronoi diagrams in parallel. The experimental results show the best performance of our method compared to state-of-the-art ones, regardless of site distribution. This paper was first submitted to SIGGRAPH Asia 2025.

cs.GR↗

arXiv2024

NeuroFly: A framework for whole-brain single neuron reconstruction

Neurons, with their elongated, tree-like dendritic and axonal structures, enable efficient signal integration and long-range communication across brain regions. By reconstructing individual neurons' morphology, we can gain valuable insights into brain connectivity, revealing the structure basis of cognition, movement, and perception. Despite the accumulation of extensive 3D microscopic imaging data, progress has been considerably hindered by the absence of automated tools to streamline this process. Here we introduce NeuroFly, a validated framework for large-scale automatic single neuron reconstruction. This framework breaks down the process into three distinct stages: segmentation, connection, and proofreading. In the segmentation stage, we perform automatic segmentation followed by skeletonization to generate over-segmented neuronal fragments without branches. During the connection stage, we use a 3D image-based path following approach to extend each fragment and connect it with other fragments of the same neuron. Finally, human annotators are required only to proofread the few unresolved positions. The first two stages of our process are clearly defined computer vision problems, and we have trained robust baseline models to solve them. We validated NeuroFly's efficiency using in-house datasets that include a variety of challenging scenarios, such as dense arborizations, weak axons, images with contamination. We will release the datasets along with a suite of visualization and annotation tools for better reproducibility. Our goal is to foster collaboration among researchers to address the neuron reconstruction challenge, ultimately accelerating advancements in neuroscience research. The dataset and code are available at https://github.com/beanli161514/neurofly

cs.CV↗

arXiv2024

Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks

We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) -- DNNs often fit target functions from low to high frequencies -- on high-dimensional benchmark datasets such as MNIST/CIFAR10 and deep neural networks such as VGG16. This F-Principle of DNNs is opposite to the behavior of most conventional iterative numerical schemes (e.g., Jacobi method), which exhibit faster convergence for higher frequencies for various scientific computing problems. With a simple theory, we illustrate that this F-Principle results from the regularity of the commonly used activation functions. The F-Principle implies an implicit bias that DNNs tend to fit training data by a low-frequency function. This understanding provides an explanation of good generalization of DNNs on most real datasets and bad generalization of DNNs on parity function or randomized dataset.

cs.LG↗

arXiv2022

Principles for generation of reverberation

In modern neuroscience, memory has been postulated to stored in neural circuits as sequential spike train and Reverberation is one of the specific example.Former research has made much progress on phenomenon description. However, the mechanism of reverberation has been unclear yet. In this study, combining electrophysiological record and numerical simulation, we confirmed a formerly unrealized neuron property that is necessary for the burst generation in reverberation. Secondly, we find out the mechanism of sequential pattern generation which clearly explained by network topology and asynchronous neurotransmitter release. In addition, we also developed a pipeline that could design the network fire in manually set order. Thirdly, we explored the dynamics of STDP learning and chased down the effects of STDP Rule in reverberation. With these understandings, we developed a STDP based learning rule which could drive the network to remember any presupposed sequence. These results indicated that neuron circuit can remember malformation through STDP rule. Those information are stored in synapse connections. By this way, animals remember information as spike sequence pattern.

q-bio.NC↗

arXiv2019

Training behavior of deep neural network in frequency domain

Why deep neural networks (DNNs) capable of overfitting often generalize well in practice is a mystery [#zhang2016understanding]. To find a potential mechanism, we focus on the study of implicit biases underlying the training process of DNNs. In this work, for both real and synthetic datasets, we empirically find that a DNN with common settings first quickly captures the dominant low-frequency components, and then relatively slowly captures the high-frequency ones. We call this phenomenon Frequency Principle (F-Principle). The F-Principle can be observed over DNNs of various structures, activation functions, and training algorithms in our experiments. We also illustrate how the F-Principle help understand the effect of early-stopping as well as the generalization of DNNs. This F-Principle potentially provides insights into a general principle underlying DNN optimization and generalization.

cs.LG↗