search

vasgaowei / pytorch_MELM

The pytorch implementation of the Min-Entropy Latent Model for Weakly Supervised Object Detection
104 stars 19 forks source link

RoIRingPoolFunction #23

Open b03505036 opened 4 years ago

b03505036 commented 4 years ago

why are you using RoIRingPoolFunction instead of RoIAlign?

And also in the lib/nets/network.py pool5_roi = self._roi_ring_pool_layer(net_conv, rois, 0., 1.0) pool5_context = self._roi_ring_pool_layer(net_conv, rois, 1.0, 1.8) pool5_frame = self._roi_ring_pool_layer(net_conv, rois, scale_inner = 1.0 / 1.8, scale_outer = 1.0)

what is different between this three parts of roi ?

Thank you!

vasgaowei commented 4 years ago

The RoiRingPoolFunction is adopted from another eccv paper, you can read this paper https://arxiv.org/abs/1609.04331 for better understanding.