This is a video describing our paper at European Conference on Computer Vision (ECCV) 2020 paper.
Title: "Towards automated testing and robustification by semantic adversarial data generation".
Authors: Rakshith Shetty, Mario Fritz and Bernt Schiele.
Abstract. Widespread application of computer vision systems in real
world tasks is currently hindered by their unexpected behavior on unseen
examples. This occurs due to limitations of empirical testing on finite
test sets and lack of systematic methods to identify the breaking points
of a trained model. In this work we propose semantic adversarial editing,
a method to synthesize plausible but difficult data points on which our
target model breaks down. We achieve this with a differentiable object
synthesizer which can change an object’s appearance while retaining its
pose. Constrained adversarial optimization of object appearance through
this synthesizer produces rare/difficult versions of an object which fool the
target object detector. Experiments show that our approach effectively
synthesizes difficult test data, dropping the performance of YoloV3 detector by more than 20 mAP points by changing the appearance of a single
object and discovering failure modes of the model. The generated semantic
adversarial data can also be used to robustify the detector through data
augmentation, consistently improving its performance in both standard
and out-of-dataset-distribution test sets, across three different datasets.