pith. sign in

arxiv: 1808.03305 · v1 · pith:TIGC3APFnew · submitted 2018-08-09 · 💻 cs.CV · cs.LG

The Elephant in the Room

classification 💻 cs.CV cs.LG
keywords objectimageaccordingaffectanalysisanothercallchanges
0
0 comments X
read the original abstract

We showcase a family of common failures of state-of-the art object detectors. These are obtained by replacing image sub-regions by another sub-image that contains a trained object. We call this "object transplanting". Modifying an image in this manner is shown to have a non-local impact on object detection. Slight changes in object position can affect its identity according to an object detector as well as that of other objects in the image. We provide some analysis and suggest possible reasons for the reported phenomena.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Metamorphic Testing of a Deep Learning based Forecaster

    cs.LG 2019-07 unverdicted novelty 5.0

    Developed 19 metamorphic relations to test correlation detection and LSTM forecasting in an outage prediction application, uncovering 8 unknown issues in the live system and detecting 65.9% of injected bugs via mutati...