IEEE

Long-Tail Class Incremental Learning via Bias Calibration With Application to Continuous Fault Diagnosis

Abstract: Class incremental learning (CIL) offers a promising framework for continuous fault diagnosis (CFD), allowing networks to accumulate knowledge from streaming industrial data and recognize new ...
IEEE

Efficient Text Style Transfer Through Robust Masked Language Model and Iterative Inference

Abstract: Emergence of Large Language Models (LLMs) have prompted researchers to exploit the abilities of such models for text style transfer (TST). However, these models are prone to hallucinations ...