Cognitive Science Research Group, Korea Brain Research Institute, Daegu, Republic of Korea.
J Vis. 2021 Sep 1;21(10):12. doi: 10.1167/jov.21.10.12.
Deep neural network (DNN) models realize human-equivalent performance in tasks such as object recognition. Recent developments in the field have enabled testing the hierarchical similarity of object representation between the human brain and DNNs. However, the representational geometry of object exemplars within a single category using DNNs is unclear. In this study, we investigate which DNN model has the greatest ability to explain invariant within-category object representations by computing the similarity between representational geometries of visual features extracted at the high-level layers of different DNN models. We also test for the invariability of within-category object representations of these models by identifying object exemplars. Our results show that transfer learning models based on ResNet50 best explained both within-category object representation and object identification. These results suggest that the invariability of object representations in deep learning depends not on deepening the neural network but on building a better transfer learning model.
深度神经网络 (DNN) 模型在物体识别等任务中实现了与人类相当的性能。该领域的最新进展使得可以测试大脑和 DNN 之间物体表示的分层相似性。然而，使用 DNN 对单个类别中的物体样本的表示几何形状尚不清楚。在这项研究中，我们通过计算不同 DNN 模型的高层视觉特征提取的表示几何之间的相似性，来研究哪种 DNN 模型具有最大的能力来解释类别内的不变物体表示。我们还通过识别物体样本来测试这些模型的类别内物体表示的不变性。我们的结果表明，基于 ResNet50 的迁移学习模型可以最好地解释类别内物体表示和物体识别。这些结果表明，深度学习中物体表示的不变性不仅取决于神经网络的加深，还取决于构建更好的迁移学习模型。
