Incremental Concept Learning via Online Generative Memory Recall

By Huaiyu Li, Weiming Dong, Bao-Gang Hu. 2019

30 citations recorded by the source corpus.

The ability to learn more concepts from incrementally arriving data over time is essential for the development of a lifelong learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as the catastrophic forgetting problem. The main reason for catastrophic forgetting is that past concept data are not available, and neural weights are changed during incrementally learning new concepts. In this article, we propose an incremental concept learning framework that includes two components, namely, ICLNet and RecallNet. ICLNet, which consists of a trainable feature extractor and a dynamic concept memory matrix, aims to learn new concepts incrementally. We propose a concept-contrastive loss to alleviate the magnitude of neural weight changes and mitigate the catastrophic forgetting problems. RecallNet aims to consolidate old concepts memory and recall pseudo samples, whereas ICLNet learns new concepts. We propose a balanced online memory recall strategy to reduce the information loss of old concept memory. We evaluate the proposed approach on the MNIST, Fashion-MNIST, and SVHN data sets and compare it with other pseudorehearsal-based approaches. Extensive experiments demonstrate the effectiveness of our approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Knowledge Capture and Replay for Continual Learning (2020, background): “On the other hand, generative replay approaches [1, 12, 22, 20] face challenges in scalability to complex datasets with many tasks, since they involve heavy training and computation associated with an auxiliary network to generate visually meaningful images for each task.”
Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning (2022, unknown): “, 2017; Belouadah & Popescu, 2019; 2020), by generative models (Kemker & Kanan, 2018; Shin et al., 2017; Li et al., 2020), or by regularized fine-tuning (Aljundi et al.”
FFNB: Forgetting-Free Neural Blocks for Deep Continual Learning (2021, methodology): “,T10 correspond to classes [51-100] while T0 is the pretraining task involving classes [1-50]).”