Preprint
Sep 2026
Don't Just Look, Intervene: Perturbation Based Region Labeling for VQA Images
Across competing automatic region-labeling mechanisms, CSGR annotations provide the most consistent gains over Cross Entropy-only finetuning in both in-domain and out-of-domain evaluations, indicating that the proposed labeling scheme captures useful region-level information.
Marko Jojic, Zhao-Nan Li, Ben Zhou
· 0 citations