잡음 레이블이 있는 강력한 학습을 위한 적응형 최근접 이웃 및 고유 벡터 기반 샘플 선택: ANNE
잡음 레이블 학습에서 단일 샘플 선택 전략을 사용하는 대신 손실 기반 샘플링과 특징 기반 샘플링을 결합한 하이브리드 적응형 전략을 사용하면 더 효과적인 샘플 선택이 가능하다.
ANNE: An Adaptive Sample Selection Method for Deep Learning with Noisy Labels Combining Nearest Neighbors and Eigenvector Approaches
ANNE, a novel sample selection method for deep learning with noisy labels, improves robustness across various noise rates by combining loss-based sampling with adaptive nearest neighbors and eigenvector-based techniques.
Potential Energy-based Mixture Model for Robust Learning from Noisy Labels
A novel Potential Energy-based Mixture Model (PEMM) that can effectively handle noisy labels by preserving the intrinsic data structure and achieving a co-stable state among class centers.
Robust Noisy Label Learning via Two-Stream Sample Distillation
A novel Two-Stream Sample Distillation (TSSD) framework is designed to train a robust network under the supervision of noisy labels by jointly considering the sample structure in feature space and the human prior in loss space.
Learning to Bootstrap Robust Models for Combating Label Noise
A simple and effective method, named Learning to Bootstrap (L2B), enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning.
© 2024 by Linnk AI