Learning Adaptive Embedding Considering Incremental Class

Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: (1) Novel class detection. The initial training data only contains incomplete classes, and streaming test data will accept unknown classes. Therefore, the model needs to not only accurately classify known classes, but also effectively detect unknown classes; (2) Model expansion. After the novel classes are detected, the model needs to be updated without re-training using the entire previous data. However, traditional CIL methods have not fully considered these two challenges. First, they are always restricted to single novel class detection within each phase and embedding confusion caused by unknown classes. Besides, they ignore the catastrophic forgetting of known categories in model update. To this end, we propose a semi-supervised style Class-Incremental Learning without Forgetting (CILF) method, which aims to learn adaptive embedding for processing novel class detection and model update in a unified framework. In detail, CILF designs to regularize classification with decoupled prototype based loss, which can improve the intra-class and inter-class structure significantly, and acquires a compact embedding representation for novel class detection in result. Then, CILF employs a learnable curriculum clustering operator to estimate the number of semantic clusters via fine-tuning the learned network, in which curriculum operator can adaptively learn the embedding in self-taught form. Therefore, CILF can detect multiple novel classes and mitigate the embedding confusion problem. Last, with the labeled streaming test data, CILF can update the network with robust regularization to mitigate the catastrophic forgetting. Consequently, CILF is able to iteratively perform novel class detection and model update. We verify the effectiveness of our model on four streaming classification tasks, and empirical studies show the superior performance of the proposed method.