FewSOL: ロボット環境における少数ショット物体学習のためのデータセット
FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
336個の実物体を9視点から撮影したRGB-D画像とセグメンテーション・姿勢・属性情報、および330個の3Dモデルから生成した合成画像を収録したデータセットを構築し、少数ショット物体分類とセグメンテーションの性能を評価した。
著者: Jishnu Jaykumar P, Yu-Wei Chao, Yu Xiang
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
We introduce the Few-Shot Object Learning (FewSOL) dataset for object recognition with a few images per object. We captured 336 real-world objects with 9 RGB-D images per object from different views. Object segmentation masks, object poses and object attributes are provided. In addition, synthetic images generated using 330 3D object models are used to augment the dataset. We investigated (i) few-shot object classification and (ii) joint object segmentation and few-shot classification with the state-of-the-art methods for few-shot learning and meta-learning using our dataset. The evaluation results show that there is still a large margin to be improved for few-shot object classification in robotic environments. Our dataset can be used to study a set of few-shot object recognition problems such as classification, detection and segmentation, shape reconstruction, pose estimation, keypoint correspondences and attribute recognition. The dataset and code are available at https://irvlutd.github.io/FewSOL.
