Class-Incremental Learning with Topological Schemas of Memory Spaces
By Xinyuan Chang, Xiaoyu Tao, Xiaopeng Hong, Xing Wei, Wei Ke, Yihong Gong. 2021
5 citations recorded by the source corpus.
Class-incremental learning (CIL) aims to incrementally learn a unified classifier for new classes emerging, which suffers from the catastrophic forgetting problem. To alleviate forgetting and improve the recognition performance, we propose a novel CIL framework, named the topological schemas model (TSM). TSM consists of a Gaussian mixture model arranged on 2D grids (2D-GMM) as the memory of the learned knowledge. To train the 2D-GMM model, we develop a novel competitive expectation-maximization (CEM) method, which contains a global topology embedding step and a local expectation-maximization fine-tuning step. Meanwhile, we choose the image samples of old classes that have the maximum posterior probability with respect to each Gaussian distribution as the episodic points. When finetuning for new classes, we propose the memory preservation loss (MPL) term to ensure episodic points still have maximum probabilities with respect to the corresponding Gaussian distribution. MPL preserves the distribution of 2D-GMM for old knowledge during incremental learning and alleviates catastrophic forgetting. Comprehensive experimental evaluations on two popular CIL benchmarks CIFAR100 and subImageNet demonstrate the superiority of our TSM.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Few-Shot Class-Incremental Learning via Relation Knowledge Distillation (2021, background): “The scenarios of incremental learning can be briefly divided into the class-incremental (Rebuffi et al. 2017; Tao et al. 2020a; Chang et al. 2021) and the task-incremental (Rajasegaran et al. 2020) ones.”