Contrast metric enhancement based on memory extraction for online class-incremental learning in image classification
In view of the catastrophic forgetting of previous knowledge in class incremental learning for image classification,existing replay-based methods focus on memory updating and sampling,while overlooking the feature relationships between old and new samples.To this end,the paper proposes a method called contrast metric enhancement based on memory extrac-tion(cME2)for Online Class-incremental Learning in Image Classification,which designs two new types of positive and neg-ative sample-pairs,enhances the reuse of old sample feature information,and strengthens the ability of model to express re-dundant features and common features.It improves the distribution of samples in embedding space based on the nearest class mean classifier.Finally,the effectiveness and efficiency of the proposed method are verified by comparison experiment and ablation experiment.
万方数据
维普
