【论文研读】Data Augmentation, Network Invariances, Pre-training with Hard Examples

目录

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (arxiv 2020.12)

Learning Invariances in Neural Networks (nips2020)

Self-supervised Pre-training with Hard Examples Improves Visual Representations (arxiv 2020.12)

---

 

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (arxiv 2020.12)

idea：

• perform a systematic study of the Copy-Paste augmentation (e.g., [13, 12]) for instance segmentation where we randomly paste objects onto an image
• we show Copy-Paste is additive with semi-supervised methods that leverage extra data through pseudo labeling (e.g. self-training).

Introduction：

• a simple strategy of randomly picking objects and pasting them at random locations on the target image provides a signifificant boost on top of b