arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.00174cs.CVcs.LG
收藏

基于Siamese神经网络的家庭成员检索

Retrieval of Family Members Using Siamese Neural Network

University of Science and Technology of China(中国科学技术大学)

Jun Yu, Guochen Xie, Mengyan Li, Xinlong Hao

摘要:

野外家庭成员检索的目的是在数据集中找到与该主题相关的家庭成员,这对于寻找走失儿童和分析亲属关系具有重要意义。然而,由于所收集的数据在年龄、性别、姿势和照明方面的多样性,这项任务总是具有挑战性。为了解决这个问题,我们提出了我们的解决方案与深连体神经网络。我们的解决方案可以分为两个部分:相似度计算和排名。在训练过程中,暹罗网络首先以两幅候选图像作为输入,产生两个特征向量。然后,计算两个向量之间的相似性与几个全连接层。而在推理过程中,我们尝试了另一种相似度计算方法,通过丢弃后面的几个全连接层,直接计算两个特征向量的余弦相似度。在相似度计算之后,我们使用排序算法合并具有相同身份的相似度得分,并根据它们的相似度输出有序列表。为了获得进一步的改进,我们尝试了不同的骨干,训练方法和相似度计算方法的组合。最后,我们提交了最佳组合作为我们的解决方案,我们的团队(ustc-nelslip)在RFIW 2020挑战赛的第三赛道上获得了良好的成绩,获得了亚军,这验证了我们的方法的有效性。我们的代码可在:https://github.com/gniknoil/FG2020-kinship

英文摘要:

Retrieval of family members in the wild aims at finding family members of the given subject in the dataset, which is useful in finding the lost children and analyzing the kinship. However, due to the diversity in age, gender, pose and illumination of the collected data, this task is always challenging. To solve this problem, we propose our solution with deep Siamese neural network. Our solution can be divided into two parts: similarity computation and ranking. In training procedure, the Siamese network firstly takes two candidate images as input and produces two feature vectors. And then, the similarity between the two vectors is computed with several fully connected layers. While in inference procedure, we try another similarity computing method by dropping the followed several fully connected layers and directly computing the cosine similarity of the two feature vectors. After similarity computation, we use the ranking algorithm to merge the similarity scores with the same identity and output the ordered list according to their similarities. To gain further improvement, we try different combinations of backbones, training methods and similarity computing methods. Finally, we submit the best combination as our solution and our team(ustc-nelslip) obtains favorable result in the track3 of the RFIW2020 challenge with the first runner-up, which verifies the effectiveness of our method. Our code is available at: https://github.com/gniknoil/FG2020-kinship

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。

↑