相关数据集
YCB benchmark dataset
该数据集来源于YCB基准数据集，包含10个不同物体的主动探索数据，每个物体100个样本。数据集通过在QB软手上集成柔性本体感受传感器，使用肌肉梭数学模型将传感器的测量值实时编码为脉冲序列。这些脉冲序列随后被输入到一个混合脉冲神经网络进行分类。该数据集有助于研究本体感受信号在人工系统中的使用，尤其是在物体分类任务中。
arXiv2025-05-23 更新1040
zte-terminators/realmirror-extra-datasets
--- license: apache-2.0 --- # Statement This dataset is only used for data augmentation and not for training! If you need to obtain benchmark train data for RealMirror, please refer to: [RealMirror tr
Hugging Face2025-11-18 更新230
ImageNet-D
该数据集名为ImageNet-D（背景子集），包含了一些带有误导性背景的图片。它是评估模型性能的标准基准，通常会使用准确率和最差群体准确率这两个指标。该数据集的任务是在误导性背景线索下的物体分类。
arXiv170
Marine Litter Dataset
An annotated marine litter dataset created by Emanuele Della Volpe to train object classification. The author was enquired but no response was given. The dataset looks to have been captured using dron
Mendeley Data2024-05-17 更新380
Spike-timing based coding in neuromimetic tactile system enables dynamic object classification
Coding dynamic tactile information in spike timing is essential to human haptic exploration and dexterous object manipulation. Conventional electronic skins generate frames of tactile signals upon int
DataONE2024-03-12 更新200
