Description
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.
Papers Using This Method
CFaults: Model-Based Diagnosis for Fault Localization in C Programs with Multiple Test Cases2024-07-12SNIPER Training: Single-Shot Sparse Training for Text-to-Speech2022-11-14Scale Normalized Image Pyramids with AutoFocus for Object Detection2021-02-10Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance2018-10-15SNIPER: Efficient Multi-Scale Training2018-05-23