Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation

1 code implementation • CVPR 2021 • Dohun Lim, HyeonSeok Lee, Sungchan Kim

We present a novel method for reliably explaining the predictions of neural networks.

Salient Explanation for Fine-grained Classification

no code implementations • 25 Sep 2019 • Kanghan Oh, Sungchan Kim, Il-Seok Oh

Explaining the prediction of deep models has gained increasing attention to increase its applicability, even spreading it to life-affecting decisions.

Classification Object Recognition