PS: DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers__ICCV2015

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool
link

精华尽在于此。 We generate hypotheses in a
sliding-window fashion over different activation layers and
show that the final convolutional layers can find the object
of interest with high recall but poor localization due to the
coarseness of the feature maps. Instead, the first layers of
the network can better localize the object of interest but with
a reduced recall.

这个想法很直观，也很符合直觉，不过论文中似乎验证的并不够完善，fig.2和fig.3感觉总欠缺点什么。