Does training with blurred images bring convolutional neural networks closer to humans with respect to robust object recognition and internal representations?
Does training with blurred images bring convolutional neural networks closer to humans with respect to robust object recognition and internal representations?
复制标题
DOI：
10.3389/fpsyg.2023.1047694
复制
发表时间：
2023
影响因子：
3.8
通讯作者：
Nishida, Shin'ya
中科院分区：
文献类型：
--
作者：
Yoshihara, Sou;Fukiage, Taiki;Nishida, Shin'ya
关键词：
有人建议，除了清晰的图像感知模糊的图像有助于发展强大的人类视觉处理。为了从计算上研究暴露于模糊图像的影响，我们在ImageNet对象识别上训练了卷积神经网络（CNN），其中包含各种清晰和模糊图像的组合。与最近的报告一致，对模糊和清晰图像的混合训练（B+S训练）使CNN在针对图像模糊变化的鲁棒对象识别方面更接近人类。B+S训练在识别形状-纹理线索冲突图像时也略微降低了CNN的纹理偏向，但效果不足以达到人类水平的形状偏向。其他测试也表明，B+S训练不能产生基于全局配置特征的鲁棒的类人对象识别。使用代表性相似性分析和零拍摄迁移学习，我们还表明，B+S-Net并不通过单独的专门子网络，一个网络用于清晰图像，另一个用于模糊图像，而是通过单个网络分析清晰和模糊图像中常见的图像特征来促进模糊鲁棒的对象识别。然而，单独的模糊训练不会自动创建像人类大脑那样的机制，其中子带信息被集成到公共表示中。我们的分析表明，模糊图像的经验可能有助于人类大脑识别模糊图像中的物体，但仅凭这一点并不能产生鲁棒的、类似人类的物体识别。
It has been suggested that perceiving blurry images in addition to sharp images contributes to the development of robust human visual processing. To computationally investigate the effect of exposure to blurry images, we trained convolutional neural networks (CNNs) on ImageNet object recognition with a variety of combinations of sharp and blurred images. In agreement with recent reports, mixed training on blurred and sharp images (B+S training) brings CNNs closer to humans with respect to robust object recognition against a change in image blur. B+S training also slightly reduces the texture bias of CNNs in recognition of shape-texture cue conflict images, but the effect is not strong enough to achieve human-level shape bias. Other tests also suggest that B+S training cannot produce robust human-like object recognition based on global configuration features. Using representational similarity analysis and zero-shot transfer learning, we also show that B+S-Net does not facilitate blur-robust object recognition through separate specialized sub-networks, one network for sharp images and another for blurry images, but through a single network analyzing image features common across sharp and blurry images. However, blur training alone does not automatically create a mechanism like the human brain in which sub-band information is integrated into a common representation. Our analysis suggests that experience with blurred images may help the human brain recognize objects in blurred images, but that alone does not lead to robust, human-like object recognition.
登录
查看更多内容
影响因子：
1.8
作者：
Jang H;Tong F
通讯作者：
Tong F
影响因子：
64.8
作者：
Le Grand, R;Mondloch, CJ;Brent, HP
通讯作者：
Brent, HP
影响因子：
5.8
作者：
Nonaka S;Majima K;Aoki SC;Kamitani Y
通讯作者：
Kamitani Y
影响因子：
1.8
作者：
Avberšek LK;Zeman A;Op de Beeck H
通讯作者：
Op de Beeck H
影响因子：
22.7
作者：
MILLER, GA
通讯作者：
MILLER, GA