Haoyu Lu

Haoyu Lu

Too late to quit,
too early to retire,
too young to die,
but too old to find a sugah daddee.

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

DeepONet and Operator Learning

4 minute read

Published:

Conventional trials of physics-informed deep learning (say, PINNs) integrates the dynamics as constraints to guide the approximation of a certain function within. An obvious problem with this idea is that such models cannot be directly applied to different initial and boundary conditions and observations. DeepONet, representing a new trial in physics-informed learning, employed some tricks to get around with this. Read more

LCA-on-the-Line Explained

2 minute read

Published:

Using in-distribution (ID) accuracy to analyze out-of-distribution (OOD) performance of models can encounter severe disintegrity, especially for models trained with diverse supervision and distributions, e.g., vision models (VM) and vision-language models (VLM). This paper, accepted at ICML 20241, proposed a novel, yet simple approach to measure OOD performance without introduction of any OOD data.

  1. For the original paper/project page, see https://elvishelvis.github.io/papers/lca/ ↩
Read more

DDPO: Aligning Diffusion Models with Human Preferences via Reinforcement Learning

8 minute read

Published:

Mainstream AIGC models, like ChatGPT and Stable Diffusion, have been drawing much attention over the recent years. Despite the massive amount of high-quality dataset, advanced network structure and loads of GPUs, one innegligible factor that contributes to their success is the use of RLHF, or reinforcement learning from human feedback. This blog is mostly based on a paper in May 2023 by the Levine Lab at UCB, and probes into how RLHF can be elegantly integrated into diffusion framework. Read more

Radiative Transfer Equation

3 minute read

Published:

Long time no see. After a tiring semester, I finally have the chance to update posts. Though there is much research progress to be talked about, it demands some more time to collect my thoughts about it. So this post will be a rather simple introduction to a famous equation in both physics and computer graphics, the radiative transfer equation (RTE). Read more

Integro-Differential Equations and Neural Network

5 minute read

Published:

Integro-Differential Equations, IDEs for short, are equations involving both partial differential and integral operators. They are commonly used in a variety of disciplines of science and engineering topics, while nonlinear IDEs are particularly difficult to solve analytically. Therefore, the idea to incorporate neural networks arises naturally. This post is dedicated to recording my understanding of IDEs and NNs. Read more

Mathematical View of Generative Models

19 minute read

Published:

Generative models, powered by AI, is a big trend now for stuff synthesis (texts, images, and even more specialize usages). This post probes into why and how they are working from a mathematical perspective. Read more

Dynamic Snake Convolution, and more

7 minute read

Published:

Thin, fragile local structures, and variable global morphologies, etc., of topological tubular structures like vessels and roads, lead to the difficulty of its accurate segmentation. This paper of DSCNet simultaneously enhance its perception for such tubular structures in 3 stages: feature extraction, feature fusion, and loss constraint. Read more

Variational Approximation for Low-dose CT Reconstruction

9 minute read

Published:

In the scenario of low-dose CT image reconstruction, supervised deep learning is widely adopted, which generally demands a dataset containing pairs of normal-dose and correspoding low-dose images and is therefore challenging in clinical situations. This paper proposed an unsupervised deep learning method to tackle this problem. Read more

Reinforcement Learning

7 minute read

Published:

Reinforcement learning is a machine learning training method based on rewarding desired behaviors and/or punishing undesired ones. In general, a reinforcement learning agent is able to perceive and interpret its environment, take actions and learn through trial and error. Read more

Origin Ensemble PET Reconstruction

10 minute read

Published:

The origin ensemble (OE) algorithm is a novel statistical method for MMSE reconstruction of emission tomography data. This method allows one to perform reconstruction entirely in the image domain, i.e. without the use of forward and backprojection operations. Read more

Radon Transform

1 minute read

Published:

The Radon transform is the transform of our n-dimensional volume to a complete set of (n-1)-dimensional line integrals. Whereas the inverse Radon transform is the transform from our complete (n-1)-dimensional line integrals back to the original image. Read more

Introduction to Topology

less than 1 minute read

Published:

Topology studies properties of spaces that are invariant under any continuous deformation. It is sometimes called “rubber-sheet geometry” because the objects can be stretched and contracted like rubber, but cannot be broken. Read more

Causal Intervention-based Class Activation Mapping

1 minute read

Published:

This paper explores the causalities among image features, contexts, and categories to eliminate the biased sobject-context entanglement in the class activation maps thus improving the accuracy of object localization. Read more

Geometric Graph

1 minute read

Published:

A graph is a powerful way of representing relationships among entities as nodes connected by edges. Sometimes nodes and edges can have spatial features, such as 3D coordinates of nodes and directions along edges. How do we reason over the topology of graphs while considering those geometric features? Read more

GraphSAGE

less than 1 minute read

Published:

GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data Read more

Locating Objects Without Bounding Boxes

1 minute read

Published:

This loss function is a modification of the average Hausdorff distance between two unordered sets of points. The proposed method has no notion of bounding boxes, region proposals, or sliding windows. Read more

Gillespie Algorithm

1 minute read

Published:

In probability theory, the Gillespie algorithm generates a statistically correct trajectory (possible solution) of a stochastic equation system for which the reaction rates are known. Mathematically, it is a variant of a dynamic Monte Carlo method and similar to the kinetic Monte Carlo methods. Read more

portfolio

publications

A virtual-pinhole PET device for improving contrast recovery and enhancing lesion detectability of a one-meter-long PET scanner: a simulation study.

Published in Physics in Medicine & Biology, Volume 68, Number 14, 2023

This paper presents a simulation study to demonstrate that the contrast recovery coefficients (CRC) and detectability of small lesions of a one-meter-long positron emission tomography (PET) scanner can be further enhanced by the integration of high resolution virtual-pinhole (VP) PET devices. Read more

Recommended citation: Jiang, J., Hua, J., Wang, H., Yuan, Z., Meng, Y., Lu, H., ... & Tai, Y. C. (2023). "A virtual-pinhole PET device for improving contrast recovery and enhancing lesion detectability of a one-meter-long PET scanner: a simulation study." Physics in Medicine and Biology.. 68(14). https://iopscience.iop.org/article/10.1088/1361-6560/acdfaf

QUANTOF: multi-GPU-based list-mode fully quantitative TOF PET image reconstruction.

Published in 2024 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD), 2024

This work introduces a multi-GPU-based list-mode fully quantitative Time-of-Flight (TOF) PET image reconstruction technique, named QUANTOF, that integrates all corrections during PET image iterative reconstruction on GPUs. Additionally, optimizations have been applied to the backprojection algorithm, resulting in a two-fold increase in speed compared to the pre-optimized version. Validation using experimental datasets from a Siemens Biograph Vision PET/CT scanner demonstrates that this technique significantly reduces reconstruction time costs while achieving exceptional quantitative accuracy. Read more

Recommended citation: Yuan, Z., Zhan, F., Lu, H., Li, C., Hou, Y., Wang, H., ... & Jiang, J. (2024, October). QUANTOF: multi-GPU-based list-mode fully quantitative TOF PET image reconstruction. In 2024 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD) (pp. 1-1). IEEE. https://ieeexplore.ieee.org/abstract/document/10657018

Multi-Annual Inventorying of Retrogressive Thaw Slumps Using Domain Adaptation

Published in Journal of Geophysical Research: Machine Learning and Computation, 2025

To enhance the model’s generalization ability, here we implemented and compared three domain adaptation methods, i.e., the classic supervised fine-tuning method and two proposed unsupervised methods: Image StyleTransfer Domain Adaptation (ISTDA) and the Tversky Adversarial Domain Adaptation (TADA) network. In our proposed ISTDA, we uniformed the contextual information of multi-temporal images by Cycle Generative Adversarial Network (CycleGAN). We introduced the Tversky loss and the automatic adjustment of weights for multiple loss functions to suppress false positives and to improve the generalization of TADA. Read more

Recommended citation: Lin, Y., Hu, X., Lu, H., Niu, F., Liu, G., Huang, L., et al. (2025). Multi-annual inventorying of retrogressive thaw slumps using domain adaptation. Journal of Geophysical Research: Machine Learning and Computation, 2, e2024JH000370. https://doi.org/10.1029/2024JH000370 https://doi.org/10.1029/2024JH000370

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post. Read more

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post. Read more