Enhancing Sampling Protocol for Point Cloud Classification Against Corruptions
School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；College of Computing, City University of Hong Kong（香港城市大学计算机学院）；SWJTU-Leeds Joint School, Southwest Jiaotong University（西南交通大学-利兹学院）
Chongshou Li, Pin Tang, Xinke Li, Yuheng Liu, Tianrui Li
Established sampling protocols for 3D point cloud learning, such as Farthest Point Sampling (FPS) and Fixed Sample Size (FSS), have long been relied upon. However, real-world data often suffer from corruptions, such as sensor noise, which violates the benign data assumption in current protocols. As a result, these protocols are highly vulnerable to noise, posing significant safety risks in critical applications like autonomous driving. To address these issues, we propose an enhanced point cloud sampling protocol, PointSP, designed to improve robustness against point cloud corruptions. PointSP incorporates key point reweighting to mitigate outlier sensitivity and ensure the selection of representative points. It also introduces a local-global balanced downsampling strategy, which allows for scalable and adaptive sampling while maintaining geometric consistency. Additionally, a lightweight tangent plane interpolation method is used to preserve local geometry while enhancing the density of the point cloud. Unlike learning-based approaches that require additional model training, PointSP is architecture-agnostic, requiring no extra learning or modification to the network. This enables seamless integration into existing pipelines. Extensive experiments on synthetic and real-world corrupted datasets show that PointSP significantly improves the robustness and accuracy of point cloud classification, outperforming state-of-the-art methods across multiple benchmarks.
Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology
College of Engineering, Peking University（北京大学工学院）；Third Hospital, Peking University Health Science Center（北京大学医学部第三医院）；Institute of Biomedical Engineering, Beijing Institute of Collaborative Innovation（北京协同创新研究院生物医学工程研究所）
Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection
School of Electrical & Computer Engineering, National Technical University Athens（雅典国立技术大学电气与计算机工程学院）；Hellenic Drones S.A.（希腊无人机公司）；School of Electronic Engineering & Computer Science, Queen Mary University of London（伦敦大学玛丽皇后学院电子工程与计算机科学学院）
Enhancing Plasticity for First Session Adaptation Continual Learning
LTCI, Télécom-Paris, Institut Polytechnique de Paris（Télécom-Paris 工程院）；University of Bergamo（贝加莫大学）；Inria at University Grenoble Alpes, LJK（格勒诺布尔阿尔卑斯大学）
Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality
Shanghai AI Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of California San Diego（加利福尼亚大学圣迭戈分校）；The University of Hong Kong（香港大学）
Benchmarking Content-Based Puzzle Solvers on Corrupted Jigsaw Puzzles
Machine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)（机器学习与数据分析实验室，人工智能生物医学工程系，弗里德里希-亚历山大-亚琛-纽伦堡大学）；Siemens Healthineers AG（西门子医疗影像股份有限公司）
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
Johns Hopkins University（约翰霍普金斯大学）；The Chinese University of Hong Kong（香港中文大学）；Intuitive Surgical Inc.（Intuitive Surgical公司）；University of Arizona（亚利桑那大学）；Chonnam National University（全州大学）；University of British Columbia（不列颠哥伦比亚大学）；Kyung Hee University（庆熙大学）；University H（大学H）
Enhancing Autism Spectrum Disorder Early Detection with the Parent-Child Dyads Block-Play Protocol and an Attention-enhanced GCN-xLSTM Hybrid Deep Learning Framework
Shandong University（山东大学）；University of Michigan（密歇根大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）
