https://github.com/xiaolonw/adversarial-frcnn
Object detection requires the ability to be robust to illumination, deformation, occlusion and intra-class variations.
data-driven strategy – collect large-scale datasets which have object instances under different conditions.
The hope is that these examples capture all possible variations of a visual concept and the classifier can then effectively model invariance to them.
long tail : How can we sample such occlusions and deformations which lie on the tail?
https://mp.weixin.qq.com/s?__biz=MzA3Mjk0OTgyMg==&mid=2651123383&idx=1&sn=c2288947a721c5b88a5752bfac2ab5a2&chksm=84e6c7e6b3914ef0099c4cde6a1f2abad7623c1241a8f25cd2fbc18461b8aeb0fcb83778d0ce&mpshare=1&scene=1&srcid=0607ffLi3ZiOtO92OBb8BtLt&pass_ticket=P1YKbdSYRiC8HMaaqQDBffu2sMVg+MSXav4J1J6rknS/Ku+ERXnonUMhNLlNJYRB#rd
