Simulating Content Consistent Vehicle Datasets with Attribute Descent
share
We simulate data using a graphic engine to augment real-world datasets, with application to vehicle re-identification (re-ID). In order for data augmentation to be effective, the simulated data should be similar to the real data in key attributes like illumination and viewpoint. We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,209 vehicles of various models in 3D with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fr'echet Inception Distance (FID). This attribute descent algorithm allows content-level domain adaptation (DA), which has advantages over existing DA methods working on the pixel level or feature level. We mix adapted VehicleX data with three vehicle re-ID datasets individually, and observe consistent improvement when the proposed attribute descent is applied. With the augmented datasets, we report competitive accuracy compared with state-of-the-art results. The VehicleX engine and code of this paper will be released.
READ FULL TEXT