Proj CDeepFuzz Paper Reading: Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness

Abstract

本文：
Task: 1. prove invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations 2. prove that on adversarial examples from transformation groups in the infinite data limit robust training can also improve accuracy on test set
实验：
数据集：CIFAR-10, SVHN, CIFAR-100

1. 证明在标准data augmentation或者adversarial training上添加regularization能够减少relative robust error 20%(CIFAR-10)且overhead最小
2. 效果甚至好于人工调整过的模型
3. 在SVHN上同时提高了test set的精确度

本栏目推荐文章
• CF1506D - Epic Transformation
• 基于正则化的图自编码器在推荐算法中的应用 Application of graph auto-encoders based on regularization in recommendation algorithms
• LLM series: Transformer
• AtCoder Regular Contest 138
• Learning Dynamic Query Combinations for Transformer-based Object** Detection and Segmentation论文阅读笔记
• [NLP复习笔记] Transformer
• RNN 和 Transformer 复杂度比较
• 挑战Transformer的新架构Mamba解析以及Pytorch复现
• 《Span-Based Joint Entity and Relation Extraction with Transformer Pre-Training》阅读笔记
• ICLR 2022: Anomaly Transformer论文阅读笔记+代码复现

Invariance-inducing transformations regularization Invariance robustnessinvariance-inducing transformations regularization invariance-inducing robustness-enhanced adversarial regularized understanding transformers robustness vision invariance contravariance covariance invariance typevar robust robustness robustness-enhanced translation augmentation robustness improving