Alleviating Catastrophic Forgetting in Facial Expression Recognition with Emotion-Centered Models

arXiv:2404.12260v1 Announce Type: cross
Abstract: Facial expression recognition is a pivotal component in machine learning, facilitating various applications. However, convolutional neural networks (CNNs) are often plagued by catastrophic forgetting, impeding their adaptability. The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. Moreover, ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. This dual approach enables CNNs to retain past knowledge while learning new tasks, enhancing their performance …

abstract adaptability adversarial applications arxiv catastrophic forgetting challenge cnns convolutional neural networks cs.cv cs.lg emotion facial expression generative generative adversarial networks however images machine machine learning networks neural networks pivotal recognition synthetic type