ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification
This addresses the need for efficient object-level mapping systems that can adapt to new objects without extensive retraining, though it is incremental as it builds on existing research trends.
The paper tackles the problem of enabling spatial AI systems to quickly learn new objects by proposing ISAR, a benchmark for single- and few-shot object instance segmentation and re-identification, including a semi-synthetic dataset, evaluation pipeline, and baseline method.
Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class, we need to build a large dataset and retrain the system. To build spatial AI systems that can quickly be taught about new objects, we need to effectively solve the problem of single-shot object detection, instance segmentation and re-identification. So far there is neither a method fulfilling all of these requirements in unison nor a benchmark that could be used to test such a method. Addressing this, we propose ISAR, a benchmark and baseline method for single- and few-shot object Instance Segmentation And Re-identification, in an effort to accelerate the development of algorithms that can robustly detect, segment, and re-identify objects from a single or a few sparse training examples. We provide a semi-synthetic dataset of video sequences with ground-truth semantic annotations, a standardized evaluation pipeline, and a baseline method. Our benchmark aligns with the emerging research trend of unifying Multi-Object Tracking, Video Object Segmentation, and Re-identification.