ZjjConan / SimAM

The official pytorch implemention of our ICML-2021 paper "SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks".

ZjjConan/SimAM Issues

关于实现的问题
Closed 2 years ago6
neural free
Updated a year ago3
请问如何用mmdection复现？
Closed 2 years ago6
大致试了下结果还是se net好点
Updated 2 years ago7
预训练模型
Closed 2 years ago2
关于mmdetection训练日志log中的一些疑惑
Closed 2 years ago2
类激活热力图是怎么实现的吗
Closed 2 years ago2
关于simam
Closed 2 years ago1
请问实验用的mmdetection是哪个版本
Closed 2 years ago
def __repr__ 的作用
Closed 3 years ago4
A typo of your paper
Updated 3 years ago2
Question about the using of the energy function
Updated 3 years ago2
/
Closed 3 years ago
Why use regularizer?
Updated 3 years ago
Hello: This work is very interesting. The article is well-founded. I manually derived the formula in the paper and found that the expression of δ²_t in the paper seems to be problematic.
Closed 3 years ago5
Fast closed-form solution about Eqn (2)
Updated 3 years ago3
Can you release the code file of your attention map?
Closed 3 years ago1
requirements.txt
Closed 3 years ago1
does the simam attention needs `detach`?
Closed 3 years ago7