Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery

TL;DR

This paper introduces a novel image generation framework using dense residual attention to synthesize traffic signs, enhancing detection and classification performance in street-view imagery, especially for rare sign classes.

Contribution

It presents a new end-to-end generative model with dense residual attention and multi-scale discriminators for realistic traffic sign synthesis to improve detection and classification.

Findings

Reduced false positives by 1.2-1.5% at 99% recall

Improved classification accuracy by 4.65%

Effective detection across many traffic sign classes

Abstract

Object detection and classification of traffic signs in street-view imagery is an essential element for asset management, map making and autonomous driving. However, some traffic signs occur rarely and consequently, they are difficult to recognize automatically. To improve the detection and classification rates, we propose to generate images of traffic signs, which are then used to train a detector/classifier. In this research, we present an end-to-end framework that generates a realistic image of a traffic sign from a given image of a traffic sign and a pictogram of the target class. We propose a residual attention mechanism with dense concatenation called Dense Residual Attention, that preserves the background information while transferring the object information. We also propose to utilize multi-scale discriminators, so that the smaller scales of the output guide the higher resolution output. We have performed detection and classification tests across a large number of traffic sign classes, by training the detector using the combination of real and generated data. The newly trained model reduces the number of false positives by 1.2 - 1.5% at 99% recall in the detection tests and an absolute improvement of 4.65% (top-1 accuracy) in the classification tests.