3 papers
cs.CV2019
Deep Closed-Form Subspace Clustering
Junghoon Seo, Jamyoung Koo, Taegyun Jeon
We propose Deep Closed-Form Subspace Clustering (DCFSC), a new embarrassingly simple model for subspace clustering with learning non-linear mapping. Compared with the previous deep…
cs.LG2019
Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps
Beomsu Kim, Junghoon Seo, SeungHyun Jeon +3
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are o…
cs.LG2018
Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative
Junghoon Seo, Jeongyeol Choe, Jamyoung Koo +3
SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input. However, there were few works that provide a rigorous t…