When Conventional Wisdom Fails: Revisiting Data Augmentation for Self-Driving Cars
<p>The original paper showed that cutout can significantly improve accuracy for vision applications. Because of this, I was surprised that when I applied it to our data, our detection mmAP decreased. I searched our data pipeline for the problem and found something even more surprising: <em>all of the augmentors we were already using were hurting performance immensely.</em></p>
<p>At the beginning of this exploration, we were using flip, crop, and weight decay regularization — a standard scheme for object detection tasks. Through an ablation study, I found that each of these hurt detection performance on our internal dataset. Removing our default augmentors resulted in a 13% mmAP* boost relative to the network’s initial performance.</p>
<p><a href="https://towardsdatascience.com/when-conventional-wisdom-fails-revisiting-data-augmentation-for-self-driving-cars-4831998c5509"><strong>Website</strong></a></p>