ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification
Loading...
Author / Producer
Date
2023-11-21
Publication Type
Dataset
ETH Bibliography
yes
Citations
Altmetric
Data
Rights / License
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.
Permanent link
Publication status
External links
Editor
Contributors
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.
Book title
Journal / series
Volume
Pages / Article No.
Publisher
ETH Zurich
Event
Edition / version
Methods
Software
Geographic location
Date collected
2023
Date created
2023
Subject
Video instance segmentation; 3D scene understanding; Video Object Segmentation
Organisational unit
03737 - Siegwart, Roland Y. (emeritus) / Siegwart, Roland Y. (emeritus)
Notes
Funding
Related publications and datasets
Is supplement to: 10.48550/arXiv.2311.02734