SNIPER

2000년 도입 · 논문 5편에서 사용

SNIPER is a multi-scale training approach for instance-level recognition tasks like object detection and instance-level segmentation. Instead of processing all pixels in an image pyramid, SNIPER selectively processes context regions around the ground-truth objects (a.k.a chips). This can help to speed up multi-scale training as it operates on low-resolution chips. Due to its memory-efficient design, SNIPER can benefit from Batch Normalization during training and it makes larger batch-sizes possible for instance-level recognition tasks on a single GPU.

출처: SNIPER: Efficient Multi-Scale Training

소개 논문: SNIPER: Efficient Multi-Scale Training