2 code implementations • 8 Apr 2024 • Zhiyuan Yang, Ryan Rad
Solar Photovoltaic (PV) technology is increasingly recognized as a pivotal solution in the global pursuit of clean and renewable energy.
no code implementations • 8 Mar 2024 • Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang, Qingfu Zhang
To address this gap, we propose a new metric termed adversarial hypervolume, assessing the robustness of deep learning models comprehensively over a range of perturbation intensities from a multi-objective optimization standpoint.
no code implementations • 29 Feb 2024 • Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Fei Liu, Zhenkun Wang, Qingfu Zhang
Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution.
no code implementations • 29 Feb 2024 • Zhiyuan Yang, Yunjiao Zhou, Lihua Xie, Jianfei Yang
We find that the tiny model after network augmentation is much easier for a teacher to distill.
1 code implementation • 22 Feb 2024 • Anqi Cheng, Zhiyuan Yang, Haiyue Zhu, Kezhi Mao
Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss.
no code implementations • 19 Jan 2024 • Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang
Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters.
1 code implementation • 7 Nov 2023 • Shengzhe Zhou, Zejian Lee, Shengyuan Zhang, Lefan Hou, Changyuan Yang, Guang Yang, Zhiyuan Yang, Lingyun Sun
Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model.
1 code implementation • 4 Nov 2023 • Fei He, Zhiyuan Yang, Mingyue Gao, Biplab Poudel, Newgin Sam Ebin Sam Dhas, Rajan Gyawali, Ashwin Dhakal, Jianlin Cheng, Dong Xu
Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yet the task of protein particle picking, integral for 3D protein structure construction, is laden with manual inefficiencies.
no code implementations • 31 Oct 2023 • Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Qingfu Zhang
In this work, we make the first attempt to incorporate the structure constraints into the whole solution set by a single Pareto set model, which can be efficiently learned by a simple evolutionary stochastic optimization method.
1 code implementation • 24 Jul 2023 • Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang
Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems.
1 code implementation • 16 Oct 2022 • Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang
This work represents the first attempt to model the Pareto set for expensive multi-objective optimization.
1 code implementation • 29 Mar 2022 • Xi Lin, Zhiyuan Yang, Qingfu Zhang
In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.
no code implementations • 8 Nov 2021 • Jianfei Guo, Zhiyuan Yang, Xi Lin, Qingfu Zhang
By representing object instances within the same category as shape and appearance variation of a shared NeRF template, our proposed method can achieve dense shape correspondences reasoning on images for a wide range of object classes.
no code implementations • ICLR 2022 • Xi Lin, Zhiyuan Yang, Qingfu Zhang
In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.
no code implementations • 11 May 2021 • Lixin Xu, Lin Li, Kunniang Liu, Jiarui Zhang, Yuanning Chang, Yunpeng Fang, Hao Yuan, Zhiyuan Yang, Jingyuan Chen, Yiyao Wang, Yajun Fang
ransportation systems have revolutionized the form of society.
no code implementations • 13 Oct 2020 • Xi Lin, Zhiyuan Yang, Qingfu Zhang, Sam Kwong
With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together.