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 2108.01958cs.CV
收藏

学习兼容的嵌入

Learning Compatible Embeddings

AiBee Inc.(爱比公司)

Qiang Meng, Chixiang Zhang, Xiaoqiang Xu, Feng Zhou

摘要:

在推出新模型时实现向后兼容性可以大大降低成本,甚至可以绕过生产中视觉检索系统对现有图库图像的功能重新编码。以前的相关工作通常利用损失用于知识蒸馏,这可能会导致性能下降或不保证兼容性。为了解决这些问题,我们提出了一个通用的框架,称为学习兼容嵌入(LCE),这是适用于跨模型的兼容性和兼容的直接/前向/后向方式的培训。我们的兼容性是通过直接或通过转换对齐模型之间的类中心,并限制新模型的更紧凑的类内分布来实现的。实验进行了广泛的情况下,如训练数据集的变化,损失函数,网络架构以及特征尺寸,并证明LCE有效地使模型的兼容性与边际牺牲的准确性。该代码将在https://github.com/IrvingMeng/LCE上提供。

英文摘要:

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses used in knowledge distillation which can cause performance degradations or not guarantee compatibility. To address these issues, we propose a general framework called Learning Compatible Embeddings (LCE) which is applicable for both cross model compatibility and compatible training in direct/forward/backward manners. Our compatibility is achieved by aligning class centers between models directly or via a transformation, and restricting more compact intra-class distributions for the new model. Experiments are conducted in extensive scenarios such as changes of training dataset, loss functions, network architectures as well as feature dimensions, and demonstrate that LCE efficiently enables model compatibility with marginal sacrifices of accuracies. The code will be available at https://github.com/IrvingMeng/LCE.

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。

↑