Bookworm continual learning: beyond zero-shot learning and continual learning
By Kai Wang, Luis Herranz, Anjan Dutta, Joost van de Weijer. 2020
6 citations recorded by the source corpus.
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning ability, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.
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
- Arthur Douillard
- Matthieu Cord
- Yifu Chen
- Arnaud Dapogny
- Eduardo Valle
- Thomas Robert
- Charles Ollion
- Bernt Schiele
In Computer Vision and Pattern Recognition
- Arthur Douillard
- Matthieu Cord
- Yifu Chen
- Arnaud Dapogny
- Bernt Schiele
- Eduardo Valle
- Thomas Robert
- Charles Ollion
Citations in the corpus
- PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Further works should investigate how to exploit the already present future information with Zeroshot [41, 40] as already done in semantic segmentation [35, 5] and explored for continual classification [71, 18].”
- Insights from the Future for Continual Learning (2020, background): “[43], released simultaneous to ours, proposed an integration of zeroshot into continual learning limited to two tasks, severely curtailing the opportunity to exploit insights from the future.”