Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition
By Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, Barbara Caputo. 2019
26 citations recorded by the source corpus.
While today’s robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will always have visual knowledge gaps. However, standard visual modules are usually built on a limited set of classes and are based on the strong prior that an object must belong to one of those classes. Identifying whether an instance does not belong to the set of known categories (i.e. open set recognition), only partially tackles this problem, as a truly autonomous agent should be able not only to detect what it does not know, but also to extend dynamically its knowledge about the world. We contribute to this challenge with a deep learning architecture that can dynamically update its known classes in an end-to-end fashion. The proposed deep network, based on a deep extension of a non-parametric model, detects whether a perceived object belongs to the set of categories known by the system and learns it without the need to retrain the whole system from scratch. Annotated images about the new category can be provided by an ‘oracle’ (i.e. human supervision), or by autonomous mining of the Web. Experiments on two different databases and on a robot platform demonstrate the promise of our approach.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Learngene: From Open-World to Your Learning Task (2021, background): “open world recognition or classification) (Bendale and Boult 2015; Mancini et al. 2019b; Shu, Xu, and Liu 2018) can be broadly defined as learning a model that can perform its intended task and then incrementally learn the new things.”
- Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks (2021, background): “tally learn unknown object from web-supervision [51]”