空间注意力机制sam_【论文解读】用于卷积神经网络的注意力机制(Attention)----CBAM: Convolutional Block Attention Module...
摘要
论文提出了Convolutional Block Attention Module(CBAM)，这是一种为卷积神将网络设计的，简单有效的注意力模块(Attention Module)。对于卷积神经网络生成的feature map，CBAM从通道和空间两个维度计算feature map的attention map，然后将attention map与输入的feature map相乘来进行特征的自适应学习。CBAM是一个轻量的通用模块，可以将其融入到各种卷积神经网络中进行端到端的训练。
主要思想
对于一个中间层的feature map：
，CBAM将会顺序推理出1维的channel attention map
以及2维的spatial attention map
，整个过程如下所示：
其中
为element-wise multiplication，首先将channel attention map与输入的feature map相乘得到
，之后计算
的spatial attention map，并将两者相乘得到最终的输出
。下图为CBAM的示意图：
CBAM的结构图
Channel attention module
feature map 的每个channel都被视为一个feature detector，channel attention主要关注于输入图片中什么(what)是有意义的。为了高效地计算channel attention，论文使用最大池化和平均池化对feature map在空间维度上进行压缩，得到两个不同的空间背景描述：
和
。使用由MLP组成的共享网络对这两个不同的空间背景描述进行计算得到channel attention map：
。计算过程如下：
其中
，
，
后使用了Relu作为激活函数。
Spatial attention module.
与channel attention不同，spatial attention主要关注于位置信息(where)。为了计算spatial attention，论文首先在channel的维度上使用最大池化和平均池化得到两个不同的特征描述
和
，然后使用concatenation将两个特征描述合并，并使用卷积操作生成spatial attention map
。计算过程如下：
其中，
表示7*7的卷积层
下图为channel attention和spatial attention的示意图：
(上)channel attention module；(下)spatial attention module
代码
环境：tensorflow 1.9
"""
@Time : 2018/10/19
@Author : Li YongHong
@Email : [email protected]
@File : test.py
"""
import tensorflow as tf
import numpy as np
slim = tf.contrib.slim
def combined_static_and_dynamic_shape(tensor):
"""Returns a list containing static and dynamic values for the dimensions.
Returns a list of static and dynamic values for shape dimensions. This is
useful to preserve static shapes when available in reshape operation.
Args:
tensor: A tensor of any type.
Returns:
A list of size tensor.shape.ndims containing integers or a scalar tensor.
"""
static_tensor_shape = tensor.shape.as_list()
dynamic_tensor_shape = tf.shape(tensor)
combined_shape = []
for index, dim in enumerate(static_tensor_shape):
if dim is not None:
combined_shape.append(dim)
else:
combined_shape.append(dynamic_tensor_shape[index])
return combined_shape
def convolutional_block_attention_module(feature_map, index, inner_units_ratio=0.5):
"""
CBAM: convolution block attention module, which is described in "CBAM: Convolutional Block Attention Module"
Architecture : "https://arxiv.org/pdf/1807.06521.pdf"
If you want to use this module, just plug this module into your network
:param feature_map : input feature map
:param index : the index of convolution block attention module
:param inner_units_ratio: output units number of fully connected layer: inner_units_ratio*feature_map_channel
:return:feature map with channel and spatial attention
"""
with tf.variable_scope("cbam_%s" % (index)):
feature_map_shape = combined_static_and_dynamic_shape(feature_map)
# channel attention
channel_avg_weights = tf.nn.avg_pool(
value=feature_map,
ksize=[1, feature_map_shape[1], feature_map_shape[2], 1],
strides=[1, 1, 1, 1],
padding='VALID'
)
channel_max_weights = tf.nn.max_pool(
value=feature_map,
ksize=[1, feature_map_shape[1], feature_map_shape[2], 1],
strides=[1, 1, 1, 1],
padding='VALID'
)
channel_avg_reshape = tf.reshape(channel_avg_weights,
[feature_map_shape[0], 1, feature_map_shape[3]])
channel_max_reshape = tf.reshape(channel_max_weights,
[feature_map_shape[0], 1, feature_map_shape[3]])
channel_w_reshape = tf.concat([channel_avg_reshape, channel_max_reshape], axis=1)
fc_1 = tf.layers.dense(
inputs=channel_w_reshape,
units=feature_map_shape[3] * inner_units_ratio,
name="fc_1",
activation=tf.nn.relu
)
fc_2 = tf.layers.dense(
inputs=fc_1,
units=feature_map_shape[3],
name="fc_2",
activation=None
)
channel_attention = tf.reduce_sum(fc_2, axis=1, name="channel_attention_sum")
channel_attention = tf.nn.sigmoid(channel_attention, name="channel_attention_sum_sigmoid")
channel_attention = tf.reshape(channel_attention, shape=[feature_map_shape[0], 1, 1, feature_map_shape[3]])
feature_map_with_channel_attention = tf.multiply(feature_map, channel_attention)
# spatial attention
channel_wise_avg_pooling = tf.reduce_mean(feature_map_with_channel_attention, axis=3)
channel_wise_max_pooling = tf.reduce_max(feature_map_with_channel_attention, axis=3)
channel_wise_avg_pooling = tf.reshape(channel_wise_avg_pooling,
shape=[feature_map_shape[0], feature_map_shape[1], feature_map_shape[2],
1])
channel_wise_max_pooling = tf.reshape(channel_wise_max_pooling,
shape=[feature_map_shape[0], feature_map_shape[1], feature_map_shape[2],
1])
channel_wise_pooling = tf.concat([channel_wise_avg_pooling, channel_wise_max_pooling], axis=3)
spatial_attention = slim.conv2d(
channel_wise_pooling,
1,
[7, 7],
padding='SAME',
activation_fn=tf.nn.sigmoid,
scope="spatial_attention_conv"
)
feature_map_with_attention = tf.multiply(feature_map_with_channel_attention, spatial_attention)
return feature_map_with_attention
#example
feature_map = tf.constant(np.random.rand(2,8,8,32), dtype=tf.float16)
feature_map_with_attention = convolutional_block_attention_module(feature_map, 1)
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
result = sess.run(feature_map_with_attention)
print(result.shape)