arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.00701cs.CV
收藏

用于单样本目标识别与检测的联合神经网络

Joint Neural Networks for One-shot Object Recognition and Detection

School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦大学玛丽皇后学院电子工程与计算机科学学院)

Camilo J. Vargas, Qianni Zhang, Ebroul Izquierdo

AI总结:

本文提出一种联合神经网络,通过比较查询与目标图像对,在训练类别不可见条件下实现单样本目标识别与检测,并在MiniImageNet和Pascal VOC上取得61.41%准确率与47.1% mAP。

摘要:

本文提出了一种新颖的联合神经网络方法,以应对具有挑战性的单样本目标识别与检测任务。受Siamese神经网络和当前最先进的多框检测方法的启发,该联合神经网络能够对训练过程中未出现的类别执行目标识别与检测。遵循单样本目标识别/检测的约束条件,训练数据集和测试数据集不包含重叠的类别,换言之,所有测试类别在训练期间均保持不可见。该联合网络架构能够通过堆叠的卷积层有效比较查询输入和目标输入的图像对,识别同一输入查询类别的模式,而无需依赖先前围绕该类别的训练。所提出的方法在MiniImageNet数据集上实现了61.41%的单样本目标识别准确率,并在使用COCO数据集训练、使用Pascal VOC数据集测试时,实现了47.1%的单样本目标检测mAP。代码可在https://github.com/cjvargasc/JNN recog和https://github.com/cjvargasc/JNN detection/获取。

英文摘要:

This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state-of-art multi-box detection approaches, the joint neural networks are able to perform object recognition and detection for categories that remain unseen during the training process. Following the one-shot object recognition/detection constraints, the training and testing datasets do not contain overlapped classes, in other words, all the test classes remain unseen during training. The joint networks architecture is able to effectively compare pairs of images via stacked convolutional layers of the query and target inputs, recognising patterns of the same input query category without relying on previous training around this category. The proposed approach achieves 61.41% accuracy for one-shot object recognition on the MiniImageNet dataset and 47.1% mAP for one-shot object detection when trained on the COCO dataset and tested using the Pascal VOC dataset. Code available at https://github.com/cjvargasc/JNN recog and https://github.com/cjvargasc/JNN detection/

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。

↑