Visual Superordinate Abstraction for Robust Concept Learning
Visual Superordinate Abstraction for Robust Concept Learning
Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to attribute perturbations and out-of-distribution compositions during inference. We ascribe the bottleneck to a failure to explore the intrinsic semantic hierarchy …