Dilip Krishnan

Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers

2021 · arXiv (Cornell University)

A discriminatively trained neural net classifier can fit the training data perfectly if all information about its input other than class membership has been discarded prior to the output layer. Surprisingly, past research has discovered …

Object-Aware Cropping for Self-Supervised Learning

2021 · arXiv (Cornell University)

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that …