COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking
This addresses the problem of evolving autonomous systems needing to track new object classes without forgetting old ones, representing an incremental advance by extending continual learning to the data association stage in MOT.
The paper tackles catastrophic forgetting in class-incremental learning for multiple object tracking by introducing COOLer, a tracker that uses contrastive learning and pseudo-labels to preserve past knowledge while learning new categories, achieving effective continual learning on datasets like BDD100K and SHIFT.
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to class-incremental learning for multiple object tracking (MOT), which is desirable to accommodate the continuously evolving needs of autonomous systems. Previous solutions for continual learning of object detectors do not address the data association stage of appearance-based trackers, leading to catastrophic forgetting of previous classes' re-identification features. We introduce COOLer, a COntrastive- and cOntinual-Learning-based tracker, which incrementally learns to track new categories while preserving past knowledge by training on a combination of currently available ground truth labels and pseudo-labels generated by the past tracker. To further exacerbate the disentanglement of instance representations, we introduce a novel contrastive class-incremental instance representation learning technique. Finally, we propose a practical evaluation protocol for continual learning for MOT and conduct experiments on the BDD100K and SHIFT datasets. Experimental results demonstrate that COOLer continually learns while effectively addressing catastrophic forgetting of both tracking and detection. The code is available at https://github.com/BoSmallEar/COOLer.