arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08887cs.CV
收藏

基于互判别知识转移的图像到视频的再识别

Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer

Alibaba Group(阿里巴巴集团)

Pichao Wang, Fan Wang, Hao Li

摘要:

图像和视频之间表示的差距使得图像到视频重新识别(I2 V Re-ID)具有挑战性,最近的工作将此问题表述为知识蒸馏(KD)过程。在本文中,我们提出了一个相互歧视的知识蒸馏框架,以更有效地将基于视频的更丰富的表示转换为基于图像的表示。具体来说,我们提出了三重对比度损失(TCL),一种新的损失KD设计。在KD过程中,TCL损失转移本地结构,利用高阶信息,并减轻教师和学生网络的异构输出的不对齐。与KD的其他损失相比,建议TCL损失选择性地将局部判别特征从教师转移到学生,使其在ReID中有效。除了TCL的损失,我们采取相互学习,以经常性的教师和学生的网络培训。大量的实验证明了我们的方法在MARS,DukeMTMC-VideoReID和VeRi-776基准测试中的有效性。

英文摘要:

The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual discriminative knowledge distillation framework to transfer a video-based richer representation to an image based representation more effectively. Specifically, we propose the triplet contrast loss (TCL), a novel loss designed for KD. During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks. Compared with other losses for KD, the proposed TCL loss selectively transfers the local discriminative features from teacher to student, making it effective in the ReID. Besides the TCL loss, we adopt mutual learning to regularize both the teacher and student networks training. Extensive experiments demonstrate the effectiveness of our method on the MARS, DukeMTMC-VideoReID and VeRi-776 benchmarks.

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。

↑