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 2301.04221cs.CVcs.LG
收藏

通过Forgestry学习动力学解释深度模型

Explaining Deep Models through Forgettable Learning Dynamics

Georgia Institute of Technology(佐治亚理工学院)

Ryan Benkert, Oluwaseun Joseph Aribido, Ghassan AlRegib

摘要:

尽管深度神经网络在无数应用中取得了巨大的成功,但解释模型行为或预测仍然是一个开放的研究问题。在本文中,我们通过分析深度神经网络在语义分割任务中的学习动态,采用一种简单而有效的方法来解决这个问题。具体来说,我们通过跟踪样本在随后的训练时期中被学习和遗忘的频率来可视化训练过程中的学习行为。这进一步允许我们获得关于类决策边界的接近度的重要信息,并识别对模型构成特定挑战的区域。受这种现象的启发,我们提出了一种新的分割方法,积极使用这些信息来改变模型中的数据表示,通过增加各种困难的区域。最后,我们表明,我们的方法始终减少了经常被遗忘的区域的数量。我们进一步评估我们的方法的分割性能。

英文摘要:

Even though deep neural networks have shown tremendous success in countless applications, explaining model behaviour or predictions is an open research problem. In this paper, we address this issue by employing a simple yet effective method by analysing the learning dynamics of deep neural networks in semantic segmentation tasks. Specifically, we visualize the learning behaviour during training by tracking how often samples are learned and forgotten in subsequent training epochs. This further allows us to derive important information about the proximity to the class decision boundary and identify regions that pose a particular challenge to the model. Inspired by this phenomenon, we present a novel segmentation method that actively uses this information to alter the data representation within the model by increasing the variety of difficult regions. Finally, we show that our method consistently reduces the amount of regions that are forgotten frequently. We further evaluate our method in light of the segmentation performance.

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。

↑