ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification
Open access
Creator
Date
2023-11-21Type
- Dataset
ETH Bibliography
yes
Altmetrics
Abstract
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000642459Contributors
Contact person: Gorlo, Nicolas
Data collector: Gorlo, Nicolas
Project member: Gorlo, Nicolas
Project member: Milano, Francesco
Project member: Blomqvist, Kenneth
Research group: Siegwart, Roland Y.
Publisher
ETH ZurichDate collected
2023Date created
2023Subject
Video instance segmentation; 3D scene understanding; Video Object SegmentationOrganisational unit
03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
Related publications and datasets
Is supplement to: https://doi.org/10.48550/arXiv.2311.02734
More
Show all metadata
ETH Bibliography
yes
Altmetrics