arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.13591cs.CVcs.AI
收藏

改进弱可识别特征小目标识别方法的选择

Chosen methods of improving small object recognition with weak recognizable features

Institute of Computer Science(计算机科学研究所);AGH University of Science and Technology(AGH科技大学);Institute of Electronics(电子研究所)

Magdalena Stachoń, Marcin Pietroń

摘要:

许多目标检测模型都在与小目标检测的几个问题方面作斗争,包括样本数量少、缺乏多样性和低特征表示。考虑到GANs属于生成模型类,它们的初始目标是学习模仿任何数据分布。使用适当的GAN模型将能够增强低精度数据,增加它们的数量和多样性。该解决方案可能导致改进的目标检测结果。此外,在深度学习模型中引入基于GAN的架构可以提高小物体识别的准确性。在这项工作中,提出了基于GAN的增强方法来改进VOC Pascal数据集上的小目标检测。该方法与不同的流行的增强策略,如对象旋转,移位等进行了比较。实验是基于FasterRCNN模型。

英文摘要:

Many object detection models struggle with several problematic aspects of small object detection including the low number of samples, lack of diversity and low features representation. Taking into account that GANs belong to generative models class, their initial objective is to learn to mimic any data distribution. Using the proper GAN model would enable augmenting low precision data increasing their amount and diversity. This solution could potentially result in improved object detection results. Additionally, incorporating GAN-based architecture inside deep learning model can increase accuracy of small objects recognition. In this work the GAN-based method with augmentation is presented to improve small object detection on VOC Pascal dataset. The method is compared with different popular augmentation strategies like object rotations, shifts etc. The experiments are based on FasterRCNN model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑