arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.02865cs.CVcs.LGcs.NE
收藏

典型性在对象分类中的作用:提高卷积神经网络的泛化能力

The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks

Rutgers University(罗格斯大学)

Babak Saleh, Ahmed Elgammal, Jacob Feldman

摘要:

深度人工神经网络在计算机视觉领域的不同任务中取得了显著进展。然而,这些模型的实证分析和调查其失败的情况下,最近受到关注。在这项工作中,我们证明了深度学习模型不能推广到与训练图像有很大不同的非典型图像。这与人类大脑中视觉系统的卓越概括能力形成对比。我们专注于卷积神经网络(CNN)作为对象识别和分类中最先进的模型;更详细地研究这个问题,并假设训练CNN模型遭受非结构化损失最小化。我们提出了计算模型,通过考虑训练图像的典型外观来提高CNN的泛化能力。通过进行广泛的一组实验,我们表明,涉及一个典型性措施可以提高一组新的图像的分类结果由一个大的利润。更重要的是,这种显著的改进是在不对目标图像集上的CNN模型进行微调的情况下实现的。

英文摘要:

Deep artificial neural networks have made remarkable progress in different tasks in the field of computer vision. However, the empirical analysis of these models and investigation of their failure cases has received attention recently. In this work, we show that deep learning models cannot generalize to atypical images that are substantially different from training images. This is in contrast to the superior generalization ability of the visual system in the human brain. We focus on Convolutional Neural Networks (CNN) as the state-of-the-art models in object recognition and classification; investigate this problem in more detail, and hypothesize that training CNN models suffer from unstructured loss minimization. We propose computational models to improve the generalization capacity of CNNs by considering how typical a training image looks like. By conducting an extensive set of experiments we show that involving a typicality measure can improve the classification results on a new set of images by a large margin. More importantly, this significant improvement is achieved without fine-tuning the CNN model on the target image set.

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。

↑