retentive专题

[Retentive R-CNN] Generalized Few-Shot Object Detection without Forgetting(CVPR. 2021)

1. Motivation 本文关注于fine-tune后的FSOD模型会在base classes上性能下降的问题。这篇文章构建了Retentive R-CNN,创新点在于Bias-Balance RPN Re-detector,用来在识别novel classes的同时,不降低原有的base classes的精度 However, the majority focus merely o