Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this problem has primarily focused on ImageNet variations (e.g., ImageNetV2, ImageNet-A). To avoid potential inherited biases in these studies, we take a different approach. Specifically, we reanalyze the ObjectNet dataset recently proposed by Barbu et al. containing objects in daily life situations. They showed a dramatic performance drop of the state of the art object recognition models on this dataset. Due to the importance and implications of their results regarding the generalization ability of deep models, we take a second look at their analysis. We find that applying deep models to the isolated objects, rather than the entire scene as is done in the original paper, results in around 20-30% performance improvement. Relative to the numbers reported in Barbu et al., around 10-15% of the performance loss is recovered, without any test time data augmentation. Despite this gain, however, we conclude that deep models still suffer drastically on the ObjectNet dataset. We also investigate the robustness of models against synthetic image perturbations such as geometric transformations (e.g., scale, rotation, translation), natural image distortions (e.g., impulse noise, blur) as well as adversarial attacks (e.g., FGSM and PGD-5). Our results indicate that limiting the object area as much as possible (i.e., from the entire image to the bounding box to the segmentation mask) leads to consistent improvement in accuracy and robustness.
SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification
Jalisco's multiclass land cover analysis and classification using a novel lightweight convnet with real-world multispectral and relief data
Dirección General de Inteligencia Gubernamental（瓜纳华托州政府情报总局）；Coordinación general de innovación Gubernamental del Gobierno del estado Jalisco（哈利斯科州政府政府创新协调局）
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
Hong Kong University of Science and Technology（香港科技大学）；Singapore University of Technology and Design（新加坡科技设计大学）；The University of Tokyo（东京大学）；Deakin University（迪肯大学）
Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital（人工智能在医疗与健康中的chair，慕尼黑技术大学及慕尼黑技术大学医院）；Department of Computing, Imperial College London, UK, and Munich Center for Machine Learning (MCML)（计算系，伦敦帝国学院，英国，以及慕尼黑机器学习中心）；Department of Internal Medicine, TUM University Hospital（内科系，慕尼黑技术大学医院）
SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）；School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
La Rochelle Université（拉罗谢尔大学）；Université Sorbonne Paris Nord（巴黎北索邦大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；AllRead Machine Learning Technologies（AllRead机器学习技术公司）
Deep-learning coupled with novel classification method to classify the urban environment of the developing world
The University of Tokyo（东京大学）；The Independent University Bangladesh（孟加拉国独立大学）；The Data and Design Lab（数据与设计实验室）；University of Dhaka（达卡大学）；United Nations University（联合国大学）
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiaotong University（上海交通大学）；Shanghai Ruijing Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属瑞金医院）；Shanghai Tenth People’s Hospital of Tongji University（同济大学附属上海市第十人民医院）；Xuzhou Central Hospital（徐州市中心医院）；Renji Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属仁济医院）；Sensetime Research（商汤科技研究院）；The First Affiliated Hospital of Zhengzhou University（郑州大学第一附属医院）；West China Hospital, Sichuan University（四川大学华西医院）
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；City University of Hong Kong（香港城市大学）；Yale University（耶鲁大学）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）
Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook
Japan Advanced Institute of Science and Technology（日本科学技术先进研究院）；University College London（伦敦大学学院）；The Hong Kong University of Science and Technology（香港科学大学）；University of Toyama（toyama大学）；Monash University（墨尔本大学）
Federated Learning for Breast Density Classification: A Real-World Implementation
NVIDIA（英伟达）；Massachusetts General Hospital（麻省总医院）；Mayo Clinic（梅奥诊所）；Stanford University（斯坦福大学）；American College of Radiology（美国放射学会）；Diagnósticos da América (DASA)（美国诊断公司（DASA））
Decomposition-Based Domain Adaptation for Real-World Font Recognition
我们提出了一个域自适应框架，以解决合成训练和真实世界的测试数据之间的域不匹配。我们展示了我们的方法上一个具有挑战性的细粒度分类问题：识别字体风格的文本图像。在这个任务中，生成大量的渲染字体示例非常容易，但很难获得真实世界的标记图像。在以前的字体识别方法中，这种真实到合成域的差距导致了对新真实数据的泛化能力差（Chen et al.（2014））。在本文中，我们介绍了一种卷积神经网络分解方法，利用一个大型的训练语料库的合成数据，以获得有效的特征进行分类。这是使用基于堆叠卷积自动编码器的自适应技术来完成的，堆叠卷积自动编码器利用大量未标记的真实世界文本图像与以特定方式预处理的合成数据相结合。所提出的DeepFont方法在我们收集的一个新的大型标记真实世界数据集上实现了高于80%（前5名）的准确率。
Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data
Heidelberg University（海德堡大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
ShiftedBronzes: Benchmarking and Analysis of Domain Fine-Grained Classification in Open-World Settings
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；School of Archaeology, Jilin University（吉林大学考古学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MoE, China（教育部知识驱动人机智能工程研究中心）
Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World
Proscia Inc.（Proscia 公司）；Boonshoft School of Medicine, Wright State University School of Medicine（莱特州立大学医学院布恩肖夫特医学院）；Dermatopathology Laboratory of Central States（中部各州皮肤病理学实验室）；University of Florida College of Medicine（佛罗里达大学医学院）；Cockerell Dermatopathology（科克雷尔皮肤病理学机构）；Sidney Kimmel Medical College at Thomas Jefferson University（托马斯杰斐逊大学西德尼·金梅尔医学院）
Evaluation of (Un-)Supervised Machine Learning Methods for GNSS Interference Classification with Real-World Data Discrepancies
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）；German Aerospace Center (DLR)（德国航空航天中心）；Friedrich-Alexander University (FAU) Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Technical University Ulm（乌尔姆大学）；University of Applied Sciences Erlangen-Nuremberg（埃尔朗根-纽伦堡应用科学大学）；Technical University in Braunschweig（布伦瑞克工业大学）；Technical University Dresden（德累斯顿工业大学）；University of Applied Sciences Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用科学大学）；Ludwig-Maximilians University (LMU) Munich（慕尼黑路德维希-马克西米利安大学）
