当前位置:
X-MOL 学术
›
arXiv.cs.CV
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2021-04-06 , DOI: arxiv-2104.02265 Suncheng Xiang, Yuzhuo Fu, Mengyuan Guan, Ting Liu
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2021-04-06 , DOI: arxiv-2104.02265 Suncheng Xiang, Yuzhuo Fu, Mengyuan Guan, Ting Liu
Employing clustering strategy to assign unlabeled target images with pseudo
labels has become a trend for person re-identification (re-ID) algorithms in
domain adaptation. A potential limitation of these clustering-based methods is
that they always tend to introduce noisy labels, which will undoubtedly hamper
the performance of our re-ID system. To handle this limitation, an intuitive
solution is to utilize collaborative training to purify the pseudo label
quality. However, there exists a challenge that the complementarity of two
networks, which inevitably share a high similarity, becomes weakened gradually
as training process goes on; worse still, these approaches typically ignore to
consider the self-discrepancy of intra-class relations. To address this issue,
in this letter, we propose a multiple co-teaching framework for domain adaptive
person re-ID, opening up a promising direction about self-discrepancy problem
under unsupervised condition. On top of that, a mean-teaching mechanism is
leveraged to enlarge the difference and discover more complementary features.
Comprehensive experiments conducted on several large-scale datasets show that
our method achieves competitive performance compared with the
state-of-the-arts.
中文翻译:
通过多重协同教学从自我差异中学习,以进行跨域人员重新识别
采用聚类策略为未标记的目标图像分配伪标记已成为域自适应中人重新识别(re-ID)算法的趋势。这些基于聚类的方法的潜在局限性在于,它们总是倾向于引入嘈杂的标签,这无疑会妨碍我们的re-ID系统的性能。为了解决此限制,一种直观的解决方案是利用协作培训来纯化伪标签质量。但是,存在一个挑战,即随着训练过程的进行,不可避免地具有高度相似性的两个网络的互补性会逐渐减弱。更糟糕的是,这些方法通常会忽略考虑类内关系的自我差异。为了解决这个问题,在这封信中,我们提出了一种针对域自适应人re-ID的多重协同教学框架,为无监督条件下的自残问题开辟了一个有希望的方向。最重要的是,利用均值教学机制来扩大差异并发现更多互补的特征。在几个大型数据集上进行的综合实验表明,与最新技术相比,我们的方法具有竞争优势。
更新日期:2021-04-08
中文翻译:
通过多重协同教学从自我差异中学习,以进行跨域人员重新识别
采用聚类策略为未标记的目标图像分配伪标记已成为域自适应中人重新识别(re-ID)算法的趋势。这些基于聚类的方法的潜在局限性在于,它们总是倾向于引入嘈杂的标签,这无疑会妨碍我们的re-ID系统的性能。为了解决此限制,一种直观的解决方案是利用协作培训来纯化伪标签质量。但是,存在一个挑战,即随着训练过程的进行,不可避免地具有高度相似性的两个网络的互补性会逐渐减弱。更糟糕的是,这些方法通常会忽略考虑类内关系的自我差异。为了解决这个问题,在这封信中,我们提出了一种针对域自适应人re-ID的多重协同教学框架,为无监督条件下的自残问题开辟了一个有希望的方向。最重要的是,利用均值教学机制来扩大差异并发现更多互补的特征。在几个大型数据集上进行的综合实验表明,与最新技术相比,我们的方法具有竞争优势。