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 2007.05104cs.CVcs.LG
收藏

$n$ -用于显著性预测的参考迁移学习

$n$-Reference Transfer Learning for Saliency Prediction

University of Minnesota(明尼苏达大学);National University of Singapore(新加坡国立大学)

Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

摘要:

得益于深度学习研究和大规模数据集,显着性预测在过去十年中取得了显著的成功。然而,在缺乏足够数据用于数据饥渴模型的新领域中预测图像上的显着性图仍然具有挑战性。为了解决这个问题,我们提出了一个用于显著性预测的Few-Shot迁移学习范例,该范例能够将从现有的大规模显著性数据集学习到的知识有效地迁移到具有有限标记示例的目标域。具体地,非常少的目标域示例被用作参考以利用源域数据集训练模型,使得训练过程可以收敛到有利于目标域的局部最小值。然后,使用参考进一步微调学习的模型。所提出的框架是基于梯度和模型不可知的。我们对不同的源域和靶域对进行了全面的实验和烧蚀研究。结果表明,该框架实现了显著的性能提升。该代码可在\url{https://github.com/luoyan407/n-reference}上公开获得。

英文摘要:

Benefiting from deep learning research and large-scale datasets, saliency prediction has achieved significant success in the past decade. However, it still remains challenging to predict saliency maps on images in new domains that lack sufficient data for data-hungry models. To solve this problem, we propose a few-shot transfer learning paradigm for saliency prediction, which enables efficient transfer of knowledge learned from the existing large-scale saliency datasets to a target domain with limited labeled examples. Specifically, very few target domain examples are used as the reference to train a model with a source domain dataset such that the training process can converge to a local minimum in favor of the target domain. Then, the learned model is further fine-tuned with the reference. The proposed framework is gradient-based and model-agnostic. We conduct comprehensive experiments and ablation study on various source domain and target domain pairs. The results show that the proposed framework achieves a significant performance improvement. The code is publicly available at \url{https://github.com/luoyan407/n-reference}.

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。

↑