DeepAI AI Chat
Log In Sign Up

Shift Variance in Scene Text Detection

by   Markus Glitzner, et al.
MVTec Software GmbH

Theory of convolutional neural networks suggests the property of shift equivariance, i.e., that a shifted input causes an equally shifted output. In practice, however, this is not always the case. This poses a great problem for scene text detection for which a consistent spatial response is crucial, irrespective of the position of the text in the scene. Using a simple synthetic experiment, we demonstrate the inherent shift variance of a state-of-the-art fully convolutional text detector. Furthermore, using the same experimental setting, we show how small architectural changes can lead to an improved shift equivariance and less variation of the detector output. We validate the synthetic results using a real-world training schedule on the text detection network. To quantify the amount of shift variability, we propose a metric based on well-established text detection benchmarks. While the proposed architectural changes are not able to fully recover shift equivariance, adding smoothing filters can substantially improve shift consistency on common text datasets. Considering the potentially large impact of small shifts, we propose to extend the commonly used text detection metrics by the metric described in this work, in order to be able to quantify the consistency of text detectors.


page 1

page 2


Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks

Recent studies have put into question the commonly assumed shift invaria...

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

Driven by deep neural networks and large scale datasets, scene text dete...

Ensembling Shift Detectors: an Extensive Empirical Evaluation

The term dataset shift refers to the situation where the data used to tr...

Shift Equivariance in Object Detection

Robustness to small image translations is a highly desirable property fo...

TedEval: A Fair Evaluation Metric for Scene Text Detectors

Despite the recent success of scene text detection methods, common evalu...

Self-consistent Reasoning For Solving Math Word Problems

Math word problems (MWPs) is a task that automatically derives solution ...

Geometry Normalization Networks for Accurate Scene Text Detection

Large geometry (e.g., orientation) variances are the key challenges in t...