We introduce Domain Aware Continual Zero-Shot Learning (DACZSL), the task of visually recognizing images of unseen categories in unseen domains sequentially. We created DACZSL on top of the DomainNet dataset by dividing it into a sequence of tasks, where classes are incrementally provided on seen domains during training and evaluation is conducted on unseen domains for both seen and unseen classes. We also proposed a novel Domain-Invariant CZSL Network (DIN), which outperforms state-of-the-art baseline models that we adapted to DACZSL setting. We adopt a structure-based approach to alleviate forgetting knowledge from previous tasks with a small per-task private network in addition to a global shared network. To encourage the private network to capture the domain and task-specific representation, we train our model with a novel adversarial knowledge disentanglement setting to make our global network task-invariant and domain-invariant over all the tasks. Our method also learns a class-wise learnable prompt to obtain better class-level text representation, which is used to represent side information to enable zero-shot prediction of future unseen classes. Our code and benchmarks are made available at https://zero-shot-learning.github.io/daczsl.
Identifer | oai:union.ndltd.org:kaust.edu.sa/oai:repository.kaust.edu.sa:10754/673833 |
Date | 29 November 2021 |
Creators | Yi, Kai |
Contributors | Elhoseiny, Mohamed, Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division, Wonka, Peter, Ghanem, Bernard, Michels, Dominik |
Source Sets | King Abdullah University of Science and Technology |
Language | English |
Detected Language | English |
Type | Thesis |
Relation | URL:https://zero-shot-learning.github.io/daczsl/ |
Page generated in 0.0015 seconds