Explorations in Texture Learning

arXiv:2403.09543v1 Announce Type: cross
Abstract: In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs and find three classes of results: associations that are strong and expected, strong and not expected, and expected but not present. Our analysis demonstrates that investigations in texture learning enable new …

abstract arxiv build classification cnns cs.cv cs.lg identification insights object relationships results texture type work