Alert button
Picture for Jiaxuan Zhao

Jiaxuan Zhao

Alert button

The Robust Semantic Segmentation UNCV2023 Challenge Results

Sep 27, 2023
Xuanlong Yu, Yi Zuo, Zitao Wang, Xiaowen Zhang, Jiaxuan Zhao, Yuting Yang, Licheng Jiao, Rui Peng, Xinyi Wang, Junpei Zhang, Kexin Zhang, Fang Liu, Roberto Alcover-Couso, Juan C. SanMiguel, Marcos Escudero-Viñolo, Hanlin Tian, Kenta Matsui, Tianhao Wang, Fahmy Adan, Zhitong Gao, Xuming He, Quentin Bouniot, Hossein Moghaddam, Shyam Nandan Rai, Fabio Cermelli, Carlo Masone, Andrea Pilzer, Elisa Ricci, Andrei Bursuc, Arno Solin, Martin Trapp, Rui Li, Angela Yao, Wenlong Chen, Ivor Simpson, Neill D. F. Campbell, Gianni Franchi

Figure 1 for The Robust Semantic Segmentation UNCV2023 Challenge Results
Figure 2 for The Robust Semantic Segmentation UNCV2023 Challenge Results
Figure 3 for The Robust Semantic Segmentation UNCV2023 Challenge Results
Figure 4 for The Robust Semantic Segmentation UNCV2023 Challenge Results

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.

* 11 pages, 4 figures, accepted at ICCV 2023 UNCV workshop 
Viaarxiv icon

Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search

Feb 06, 2023
Chao Wang, Licheng Jiao, Jiaxuan Zhao, Lingling Li, Xu Liu, Fang Liu, Shuyuan Yang

Figure 1 for Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
Figure 2 for Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
Figure 3 for Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
Figure 4 for Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search

The construction of machine learning models involves many bi-level multi-objective optimization problems (BL-MOPs), where upper level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of sub-problems and the complex dependency across UL solutions and LL weights, an UL solution is feasible if and only if the LL weight is Pareto optimal. It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution. This paper proposes a bi-level multi-objective learning framework (BLMOL), coupling the above decision-making process with the optimization process of the UL-MOP by introducing LL preference $r$. Specifically, the UL variable and $r$ are simultaneously searched to minimize multiple UL objectives by evolutionary multi-objective algorithms. The LL weight with respect to $r$ is trained to minimize multiple LL objectives via gradient-based preference multi-objective algorithms. In addition, the preference surrogate model is constructed to replace the expensive evaluation process of the UL-MOP. We consider a novel case study on multi-task graph neural topology search. It aims to find a set of Pareto topologies and their Pareto weights, representing different trade-offs across tasks at UL and LL, respectively. The found graph neural network is employed to solve multiple tasks simultaneously, including graph classification, node classification, and link prediction. Experimental results demonstrate that BLMOL can outperform some state-of-the-art algorithms and generate well-representative UL solutions and LL weights.

* Submitted to IEEE TEVC 
Viaarxiv icon

A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks

Apr 07, 2022
Chao Wang, Jiaxuan Zhao, Lingling Li, Licheng Jiao, Jing Liu, Kai Wu

Figure 1 for A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
Figure 2 for A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
Figure 3 for A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
Figure 4 for A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks

Influence maximization is a key issue for mining the deep information of social networks, which aims to select a seed set from the network to maximize the number of influenced nodes. To evaluate the influence spread of a seed set efficiently, existing works have proposed some proxy models (transformations) with lower computational costs to replace the expensive Monte Carlo simulation process. These alternate transformations based on network prior knowledge induce different search behaviors with similar characteristics from various perspectives. For a specific case, it is difficult for users to determine a suitable transformation a priori. Keeping those in mind, we propose a multi-transformation evolutionary framework for influence maximization (MTEFIM) to exploit the potential similarities and unique advantages of alternate transformations and avoid users to determine the most suitable one manually. In MTEFIM, multiple transformations are optimized simultaneously as multiple tasks. Each transformation is assigned an evolutionary solver. Three major components of MTEFIM are conducted: 1) estimating the potential relationship across transformations based on the degree of overlap across individuals (seed sets) of different populations, 2) transferring individuals across populations adaptively according to the inter-transformation relationship, 3) selecting the final output seed set containing all the proxy model knowledge. The effectiveness of MTEFIM is validated on four real-world social networks. Experimental results show that MTEFIM can efficiently utilize the potentially transferable knowledge across multiple transformations to achieve highly competitive performance compared to several popular IM-specific methods. The implementation of MTEFIM can be accessed at https://github.com/xiaofangxd/MTEFIM.

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
Viaarxiv icon

LUAI Challenge 2021 on Learning to Understand Aerial Images

Aug 30, 2021
Gui-Song Xia, Jian Ding, Ming Qian, Nan Xue, Jiaming Han, Xiang Bai, Micheal Ying Yang, Shengyang Li, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, Liangpei Zhang, Qiang Zhou, Chao-hui Yu, Kaixuan Hu, Yingjia Bu, Wenming Tan, Zhe Yang, Wei Li, Shang Liu, Jiaxuan Zhao, Tianzhi Ma, Zi-han Gao, Lingqi Wang, Yi Zuo, Licheng Jiao, Chang Meng, Hao Wang, Jiahao Wang, Yiming Hui, Zhuojun Dong, Jie Zhang, Qianyue Bao, Zixiao Zhang, Fang Liu

Figure 1 for LUAI Challenge 2021 on Learning to Understand Aerial Images
Figure 2 for LUAI Challenge 2021 on Learning to Understand Aerial Images
Figure 3 for LUAI Challenge 2021 on Learning to Understand Aerial Images
Figure 4 for LUAI Challenge 2021 on Learning to Understand Aerial Images

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.

* 7 pages, 2 figures, accepted by ICCVW 2021 
Viaarxiv icon

Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy

Jun 14, 2021
Zhicheng Guo, Jiaxuan Zhao, Licheng Jiao, Xu Liu

Figure 1 for Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy
Figure 2 for Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy
Figure 3 for Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy
Figure 4 for Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy

We propose a balanced coarsening scheme for multilevel hypergraph partitioning. In addition, an initial partitioning algorithm is designed to improve the quality of k-way hypergraph partitioning. By assigning vertex weights through the LPT algorithm, we generate a prior hypergraph under a relaxed balance constraint. With the prior hypergraph, we have defined the Wasserstein discrepancy to coordinate the optimal transport of coarsening process. And the optimal transport matrix is solved by Sinkhorn algorithm. Our coarsening scheme fully takes into account the minimization of connectivity metric (objective function). For the initial partitioning stage, we define a normalized cut function induced by Fiedler vector, which is theoretically proved to be a concave function. Thereby, a three-point algorithm is designed to find the best cut under the balance constraint.

Viaarxiv icon