Anuraag Gadehothur Karnam

EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations

Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations. Existing evaluations usually score segmentation, single-image factor prediction, or downstream accuracy, but these tests do not directly ask whether a per-object representation behaves correctly under a contr...