ZJULearning / RMI

This is the code for the NeurIPS 2019 paper Region Mutual Information Loss for Semantic Segmentation.

ZJULearning/RMI Issues

RMI
Closed a year ago1
Please do not raise issues here. This repo is archived and will no longer be maintained. Some 3rd party links maybe helpful in the content.
Closed 2 years ago
Please do not raise issues here. This repo is archived and will no longer be maintained. Some 3rd party links maybe helpful in the content.
Updated 2 years ago
Effect of resizing image & mask without keeping width-height ratio in the data augmentation
Updated 2 years ago3
How to weight some examples if loss may be negative
Updated 2 years ago1
The RMI loss provides negative loss
Closed 5 years ago3
two classification tasks with output channel = 1
Closed 3 years ago4
The intuition behind RMI loss
Closed 3 years ago2
RuntimeError: CUDA error: an illegal memory access was encountered
Closed 3 years ago2
cholesky_cuda: For batch 0: U(1,1) is zero, singular U.
Closed 4 years ago4
Comparison with the Potential Energy Loss on Gibbs distribution
Closed 3 years ago2
Sample weights for RMI loss
Closed 3 years ago4
Use CRF as post-process in image segmentation
Closed 3 years ago4
Benchmarking on Cityscapes
Closed 4 years ago3
Training a DeepLabv3 model with output_stride=16, crop_size=513, and batch_size=8 on two 2080Ti GPUs
Closed 4 years ago3
Negative RMI loss
Closed 4 years ago1
The RMI loss does not change too much
Closed 4 years ago4
Hi! Can the RMI loss be used to measure the similarity of two natural images？
Closed 4 years ago1
-
Closed 4 years ago
Not available to download ResNet101 pretrained model.
Closed 4 years ago3
About setting of baseline
Closed 5 years ago2