Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting.
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning.
To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for class and attribute information respectively.
In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet.
Ranked #47 on Image Classification on STL-10
Our approach is among the three best to tackle the M2CAI Workflow challenge.