Online Descriptor Enhancement via Self-Labelling Triplets for Visual Data Association.

We propose a self-supervised method for incrementally refining visual descriptors to improve performance in the task of object-level visual data association. Our method optimizes deep descriptor generators online, by fine-tuning a widely available network pre-trained for image classification. We show that earlier layers in the network outperform later-stage layers for the data association task while also allowing for a 94% reduction in the number of parameters, enabling the online optimization. We show that choosing positive examples separated by large temporal distances and negative examples close in the descriptor space improves the quality of the learned descriptors for the multi-object tracking task. Finally, we demonstrate a MOTA score of 21.25% on the 2D-MOT-2015 dataset using visual information alone, outperforming methods that incorporate motion information.