Search Results for author: Jake Lee

Found 4 papers, 1 papers with code

What Does CNN Shift Invariance Look Like? A Visualization Study

1 code implementation9 Nov 2020 Jake Lee, Junfeng Yang, Zhangyang Wang

We present the results of three experiments comparing representations of millions of images with exhaustively shifted objects, examining both local invariance (within a few pixels) and global invariance (across the image frame).

Interpretable Discovery in Large Image Data Sets

no code implementations21 Jun 2018 Kiri L. Wagstaff, Jake Lee

Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e. g., airport security) to science (observations that don't fit a given theory can lead to new discoveries).

General Classification Novelty Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.