For fine-grained editing and manipulation, they also require fine-grained semantic or instance maps that are tedious to produce manually.

Surprisingly, we show that even the addition ofnon-realistic random data (generated byGaussian sampling) can improverobustness.

Inthese methods, for an input, an explanation is in the form of a contrast point differing in very few features from the original input and lying inadifferent class. Otherworks tryto build globally interpretable models likedecision trees and rule lists based onthe datausing actual labels orbased ontheblack-box models predictions.

We introduce quantization with incoherence processing (QuIP), a new method based on the insight that quantization benefits from incoherent weight and Hessian matrices, i.e., from the weights being even in magnitude and the

We begin by proving the lower bound on coverage. The formal proof of this statement is standard at this point, so we simply refer to [3] for the remaining technical details. The proof for the upper bound also immediatelyfollowsfrom(S6)byapplyingLemma2in[3]. The proof is essentially an application of the main result in [2]. This will become apparent after we reduce our claim to the setting in the aforementioned paper.