Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions
Robotics and Artificial Intelligence Laboratory, Technological University of Uruguay(机器人与人工智能实验室,乌拉圭技术大学);Artificial Intelligence Laboratory, Technological University of Uruguay(人工智能实验室,乌拉圭技术大学)
Pamela Barboza, Víctor Castelli, Belén Pereira, Ricardo Grando, Bruna de Vargas, Augusto Calfani
备注:
Accepted at the International Conference on Data Science, Technology and Applications (DATA) 2026
Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. The related literature on transformer-based detectors lack information regarding the impact of backbone scale and environmental settings on model performance. This work presents a comparative evaluation of RT-DETR for detecting round objects under environmental and hyperparameter variations relevant to competitive robotics. Four ResNet backbones (ResNet18, ResNet34, ResNet50, and ResNet101) were compared using dropout rates, analyzing their effect on confidence and accuracy. All models were trained under the same configuration and evaluated under changes in lighting and background contrast. Environmental conditions primarily impact prediction confidence, while inference latency remains largely unaffected and classification accuracy stays consistently high, approaching or above 1.00 in most cases. Two distinct behaviors were observed. Under illumination variation, ResNet50 achieves the best trade-off, combining near-perfect accuracy, confidence values up to approximately 0.869 and latency around 0.058-0.059 ms. Under background variation, ResNet34 provides the most balanced performance, reaching near-perfect accuracy and higher confidence values up to approximately 0.887. These results indicate that the optimal architecture depends on the type of environmental variation, with intermediate-depth models offering the best balance between performance and efficiency.
Reproducible Benchmarking for Lung Nodule Detection and Malignancy Classification Across Multiple Low-Dose CT Datasets
Duke University School of Medicine(杜克大学医学院);Pratt School of Engineering, Duke University(杜克大学普拉特工程学院);University of Colorado(科罗拉多大学);Duke University(杜克大学)
Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset
School of Information Technology, Deakin University(德肯大学信息科技学院);Department of Head and Neck Surgery, Kasturba Medical College, Manipal Academy of Higher Education(曼谷医学院头颈外科部门,曼谷高等教育学院);Department of Radiodiagnosis and Imaging, Kasturba Medical College, Manipal Academy of Higher Education(曼谷医学院放射诊断与影像部门,曼谷高等教育学院);Manipal Institute of Technology, Manipal Academy of Higher Education(曼谷技术学院,曼谷高等教育学院)
Benchmarking Deep Learning Frameworks for Automated Diagnosis of Ocular Toxoplasmosis: A Comprehensive Approach to Classification and Segmentation
Kookmin University(国民大学);Bangladesh University of Engineering and Technology (BUET)(孟加拉国工程技术大学(BUET));Institute of Research, Innovation, Incubation and Commercialization (IRIIC), United International University (UIU)(联合国际大学(UIU)研究、创新、孵化与商业化研究所(IRIIC));McKelvey School of Engineering, Washington University in St. Louis(圣路易斯华盛顿大学麦凯尔维工程学院)
International Digital Economy Academy (IDEA)(国际数字经济研究院(IDEA));University of Science and Technology of China(中国科学技术大学);Peking University(北京大学);Microsoft Research Asia(微软亚洲研究院);Microsoft Research, Redmond(微软雷德蒙德研究院)
OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records
The First Affiliated Hospital, Jiangxi Medical College, Nanchang University(南昌大学江西医学院第一附属医院);Nanchang University(南昌大学);Georgia Institution of Technology(佐治亚理工学院)
Benchmarking Foundation Models for Renal Lesion Stratification in CT
Charité - Universitätsmedizin Berlin, Department of Radiology(柏林夏里特大学医学院放射科);Radboudumc, Diagnostic Image Analysis Group(拉德堡德大学医学中心影像分析组);Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich(慕尼黑技术大学慕尼黑大学医院克林克姆右岸诊所);Charité - Universitätsmedizin Berlin, Institute of Neuroradiology(柏林夏里特大学医学院神经放射科);German Heart Center, TUM University Hospital, Technical University of Munich(德国心脏中心,慕尼黑技术大学慕尼黑大学医院)
Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification
Technische Hochschule Ingolstadt(英戈尔施塔特应用技术大学);University of Veterinary Medicine, Vienna(维也纳兽医大学);Center for AI and Data Science, Julius-Maximilians-Universität Würzburg(维尔茨堡大学朱利叶斯-马克西米利安人工智能与数据科学中心);Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);Flensburg University of Applied Sciences(弗伦斯堡应用技术大学)
Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography
Gianmarco Spinaci Department of Classical Philology and Italian Studies, University of Bologna, Italy Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy(Gianmarco Spinaci 文艺复兴研究系,博洛尼亚大学,意大利 塔蒂别墅,哈佛大学意大利文艺复兴研究中心,佛罗伦萨,意大利);Lukas Klic Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy(Lukas Klic 塔蒂别墅,哈佛大学意大利文艺复兴研究中心,佛罗伦萨,意大利);Giovanni Colavizza Department of Classical Philology and Italian Studies, University of Bologna, Italy Department of Communication, University of Copenhagen, Denmark(Giovanni Colavizza 文艺复兴研究系,博洛尼亚大学,意大利 传播系,哥本哈根大学,丹麦)
Weed Recognition using Deep Learning Techniques on Class-imbalanced Imagery
Murdoch University(默多克大学);Department of Primary Industries and Regional Development, Western Australia(西澳大利亚州初级产业与区域发展部);University of South Australia(南澳大学)
SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST)(电气工程与计算机科学学院,国立科学与技术大学(NUST));Smart Data & Knowledge Services, German Research Center for Artificial Intelligence (DFKI)(智能数据与知识服务,德国人工智能研究中心(DFKI))
Digital Typhoon Dataset V3: Benchmarking for Multi-spectral Extension and Analyzing Systematic Bias in Intensity Regression
National Institute of Informatics(信息学国立研究院);Typhoon Science and Technology Research Center, Yokohama National University(横滨国立大学台风科学技术研究中心);University of Artois(阿图瓦大学);University of Buenos Aires(布宜诺斯艾利斯大学);Hanoi University of Science and Technology(河内理工大学);RWTH Aachen University(亚琛工业大学)
Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans
Hong Kong Baptist University(香港浸会大学);Hong Kong University of Science and Technology(香港科技大学);Hangzhou Dianzi University(杭州电子科技大学);Tsinghua University(清华大学)
COVID-19疫情已在全球蔓延数月。由于其传播性和高致病性严重威胁着人们的生命,因此准确快速地检测COVID-19感染至关重要。最近的许多研究表明,基于深度学习(DL)的解决方案可以帮助基于胸部CT扫描检测COVID-19。然而,大多数现有的工作集中在2D数据集,这可能会导致低质量的模型,因为真正的CT扫描是3D图像。此外,报告的结果跨越了不同数据集的广泛范围,比较相对不公平。在本文中,我们首先使用三种最先进的3D模型(ResNet 3D 101,DenseNet 3D 121和MC 318)在三个公开的胸部CT扫描数据集上建立基线性能。然后,我们提出了一个可区分的神经结构搜索(DNAS)框架,自动搜索的3D DL模型的3D胸部CT扫描分类与Gumbel Softmax技术,以提高搜索效率。我们进一步利用类激活映射(CAM)技术对我们的模型提供的结果的可解释性。实验结果表明,我们的自动搜索模型(CovidNet 3D)在三个数据集上的性能优于基线人类设计的模型,模型大小小几十倍,准确性更高。此外,结果还验证了CAM可以很好地应用于CovidNet 3D中的COVID-19数据集,为医疗诊断提供可解释性。
IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networks
Faculty of Automatic Control;Computers, National University of Science;National Institute for Research \& Development in Informatics - ICI Bucharest, Bucharest, Romania
Benchmarking and scaling of deep learning models for land cover image classification
Institute of Astronomy, Astrophysics, Space Applications & Remote Sensing, National Observatory of Athens(雅典国家天文台天文、天体物理、空间应用与遥感研究所);Harokopio University of Athens(雅典哈罗科皮奥大学);University of the Peloponnese(伯罗奔尼撒大学)
Towards benchmarking Western Bluebird detection in the wild
Universidad Nacional Autónoma de México(墨西哥国立自治大学);Universidad Autónoma de Tlaxcala(特拉克斯卡拉自治大学);The University of Texas at El Paso(德克萨斯大学埃尔帕索分校);INAOE(国家天体物理、光学与电子学研究所)
Benchmarking CNN and Transformer-Based Object Detectors for UAV Solar Panel Inspection
Faculty of Engineering, University of Moratuwa(摩图瓦大学工程学院);STEM College, School of Computing Technologies, RMIT University(皇家墨尔本理工学院计算机技术学院);School of Engineering, University of Southern Queensland(南方昆士兰大学工程学院)
Modern Backbones Improve Multi-task DETR for Mammography Classification and Lesion Localization
University of Technology Sydney(悉尼科技大学);Saigon Precision Medicine Research Center(西贡精准医学研究中心);College of Medicine, Taipei Medical University(台北医学大学医学院);Le Qui Don Technical University(黎文谍技术大学);National Central University(中央大学);AIBioMed Research Group, Taipei Medical University(台北医学大学AIBioMed研究组)
Replication Study and Benchmarking of Real-Time Object Detection Models
Département de physique, de génie physique et d’optique, Université Laval(物理、物理工程与光学系,拉瓦尔大学);Département de génie électrique et de génie informatique, Université Laval(电气工程与计算机工程系,拉瓦尔大学);Département d’informatique et de génie logiciel, Université Laval(计算机科学与软件工程系,拉瓦尔大学)
Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Institute for Infocomm Research (I2R), the Agency for Science, Technology and Research (A*STAR)(资讯通信研究院(I2R),新加坡科技研究局(A*STAR));Zhejiang University(浙江大学)
Tsinghua University(清华大学);International Digital Economy Academy (IDEA)(国际数字经济研究院);Alibaba Group(阿里巴巴集团);The Hong Kong University of Science and Technology(香港科技大学);South China University of Technology(华南理工大学)
Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane Detection
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);School of Vehicle and Mobility, Tsinghua University(清华大学车辆与 Mobility 学院)