We perform extensive experiments to confirm the effectiveness of AnyChange for zero-shot change detection.

NN-LM (Khandelwal et al., 2020) modify the LM output with a non-parametric Work done during internship at Meta. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

First, the pre-training is only performed on neural data from the sensorimotor network (M1, PMd, S1) which limits the applicability of these approaches to whole-brain analyses.

In these methods, an input view is geometrically warped to novel views with estimated depth maps, then the warped image is inpainted by T2I models.