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 2104.09866cs.CVcs.AIcs.LG
收藏

Distill on the Go:自监督学习中的在线知识蒸馏

Distill on the Go: Online knowledge distillation in self-supervised learning

Advanced Research Lab NavInfo Europe(四维图新欧洲高级研究实验室)

Prashant Bhat, Elahe Arani, Bahram Zonooz

摘要:

自监督学习解决了不需要注释来学习特征表示的借口预测任务。对于视觉任务,仅从输入数据创建诸如预测旋转、解决拼图的借口任务。然而,预测这些已知信息有助于学习对下游任务有用的表示。然而,最近的研究表明,更广泛和更深入的模型比更小的模型更受益于自监督学习。为了解决较小模型的自监督预训练问题,我们提出了Distill-on-the-Go(DoGo),这是一种自监督学习范式,使用单阶段在线知识蒸馏来提高较小模型的表示质量。我们采用深度相互学习策略,其中两个模型相互协作学习以改进彼此。具体来说,每个模型都是使用自监督学习和蒸馏来训练的,蒸馏将每个模型的相似性分数的softmax概率与对等模型的相似性分数对齐。我们在多个基准数据集,学习目标和架构上进行了广泛的实验,以证明我们所提出的方法的潜力。我们的研究结果表明,在存在噪声和有限的标签和泛化到分布外的数据显着的性能增益。

英文摘要:

Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data. Yet, predicting this known information helps in learning representations useful for downstream tasks. However, recent works have shown that wider and deeper models benefit more from self-supervised learning than smaller models. To address the issue of self-supervised pre-training of smaller models, we propose Distill-on-the-Go (DoGo), a self-supervised learning paradigm using single-stage online knowledge distillation to improve the representation quality of the smaller models. We employ deep mutual learning strategy in which two models collaboratively learn from each other to improve one another. Specifically, each model is trained using self-supervised learning along with distillation that aligns each model's softmax probabilities of similarity scores with that of the peer model. We conduct extensive experiments on multiple benchmark datasets, learning objectives, and architectures to demonstrate the potential of our proposed method. Our results show significant performance gain in the presence of noisy and limited labels and generalization to out-of-distribution data.

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。

↑