Variable Few Shot Class Incremental and Open World Learning

Touqeer Ahmad, Akshay Raj Dhamija, Mohsen Jafarzadeh, Steve Cruz, Ryan Rabinowitz, Chunchun Li, Terrance E. Boult; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 3688-3699


Prior work on few-shot class incremental learning has operated with an unnatural assumption: the number of ways and number of shots are assumed to be known and fixed e.g., 10-ways 5-shots, 5-ways 5-shots, etc. Hence, we refer to this setting as Fixed-Few-Shot Class Incremental Learning (FFSCIL). In practice, the pre-specified fixed number of classes and examples per class may not be available, meaning one cannot update the model. Evaluation of FSCIL approaches in such unnatural settings renders their applicability questionable for practical scenarios where such assumptions do not hold. To mitigate the limitation of FFSCIL, we propose Variable-Few-Shot Class Incremental Learning (VFSCIL) and demonstrate it with Up-to N-Ways, Up-to K-Shots class incremental learning; wherein each incremental session, a learner may have up to N classes and up to K samples per class. Consequently, conventional FFSCIL is a special case of herein introduced VFSCIL. Further, we extend VFSCIL to a more practical problem of Variable-Few-Shot Open-World Learning (VFSOWL), where an agent is not only required to perform incremental learning, but must detect unknown samples and enroll only those that it detects correctly. We formulate and study VFSCIL and VFSOWL on two benchmark datasets conventionally employed for FFSCIL i.e., Caltech-UCSD Birds-200-2011 (CUB200) and miniImageNet. First, to serve as a strong baseline, we extend the state-of-the-art FSCIL approach to operate in Up-to N-Ways, Up-to K-Shots class incremental and open-world settings. Then, we propose a novel but simple approach for VFSCIL/VFSOWL where we leverage the current advancements in self-supervised feature learning. Utilizing both benchmark datasets, our proposed approach outperforms the strong baseline on the conventional FFSCIL setting and newly introduced VFSCIL/VFSOWL settings. Our code is available at:

Related Material

[pdf] [supp]
@InProceedings{Ahmad_2022_CVPR, author = {Ahmad, Touqeer and Dhamija, Akshay Raj and Jafarzadeh, Mohsen and Cruz, Steve and Rabinowitz, Ryan and Li, Chunchun and Boult, Terrance E.}, title = {Variable Few Shot Class Incremental and Open World Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {3688-3699} }