Decoupled Self-Supervised Subspace Classifier for Few-Shot Class-Incremental SAR Target Recognition

Synthetic aperture radar automatic target recognition (SAR ATR) has ushered in a new era dominated by deep-learning (DL) techniques. However, the DL-based recognition systems inevitably confront <italic>catastrophic forgetting</italic> for learned knowledge and <italic>overfitting</italic> for the n...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yan Zhao, Lingjun Zhao, Siqian Zhang, Li Liu, Kefeng Ji, Gangyao Kuang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2024-01-01
coleção:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Assuntos:	Class-incremental learning (CIL) few-shot class-incremental learning (FSCIL) self-supervised learning (SSL) subspace classification synthetic aperture radar (SAR) target recognition
Acesso em linha:	https://ieeexplore.ieee.org/document/10663261/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!