EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder

arXiv:2404.13770v1 Announce Type: cross
Abstract: Image classification is a fundamental task in computer vision, and the quest to enhance DNN accuracy without inflating model size or latency remains a pressing concern. We make a couple of advances in this regard, leading to a novel EncodeNet design and training framework. The first advancement involves Converting Autoencoders, a novel approach that transforms images into an easy-to-classify image of its class. Our prior work that applied the Converting Autoencoder and a simple classifier …

abstract accuracy advances arxiv autoencoder boosting classification computer computer vision cs.ai cs.cv cs.lg design dnn entropy framework fundamental generalized image latency novel quest regard training type vision