Artificial neural networks (ANNs) have become an important tool for image classification with many applications in research and industry. However, it remains largely unknown how relevant image features are selected and how data properties affect this process. In particular, we are interested whether the abstraction level of image cues correlating with class membership influences feature selection. We perform experiments with binary images that contain a combination of cues, representing two different levels of abstractions: one is a pattern drawn from a random distribution where class membership correlates with the statistics of the pattern, the other a combination of symbol-like entities, where the symbolic code correlates with class membership. When the network is trained with data in which both cues are equally significant, we observe that the cues at the lower abstraction level, i.e., the pattern, is learned, while the symbolic information is largely ignored, even in networks with many layers. Symbol-like entities are only learned if the importance of low-level cues is reduced compared to the high-level ones. These findings raise important questions about the relevance of features that are learned by deep ANNs and how learning could be shifted towards symbolic features.
Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics
UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands（乌得勒支大学阿姆斯特丹分校博世Delta实验室）；The University of Chicago, Chicago, USA（芝加哥大学）；Johns Hopkins University, Baltimore, USA（约翰霍普金斯大学）
Multi-dimension Geospatial feature learning for urban region function recognition
Beijing University of Posts and Telecommunications（北京邮电大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；City University of Hong Kong（香港城市大学）
