Self-Adversarial-Training（SAT）

SAT类似数据增强
对抗样本的定义：以图像样本为例,在原样本上加入一些轻微的扰动，使得在人眼分辨不出差别的情况下，诱导模型进行错误分类。
如图所示，Input（Panda图像）+ 噪音点 = Output（误判为gibbon图像）

DropBlock

【Dropout】:(b)图中的“x”，代表的是扔掉的像素，就是没有激活的像素，但是网络还是会从dropout掉的激活单元附近学习到同样的信息的【dropout是对神经元的失活，所以对应相应的像素点如图(b)】
【Dropblock】：©图把整块信息dropout掉，就不能学习到这片区域的信息了，可能学到边缘的信息。通过dropout掉一部分相邻的整片的区域(比如头和脚)，网络就会去注重学习狗的别的部位的特征，来实现正确分类，从而表现出更好的泛化。
论文 DropBlock: A regularization method for convolutional networks
Github：https://github.com/miguelvr/dropblock
根据论文结果可知，在coco数据集上可以将准确率提高1.6%

# 代码实现
import torch
import torch.nn.functional as F
from torch import nn

class DropBlock2D(nn.Module):
    r"""Randomly zeroes 2D spatial blocks of the input tensor.
    As described in the paper
    `DropBlock: A regularization method for convolutional networks`_ ,
    dropping whole blocks of feature map allows to remove semantic
    information as compared to regular dropout.
    Args:
        drop_prob (float): probability of an element to be dropped.
        block_size (int): size of the block to drop
    Shape:
        - Input: `(N, C, H, W)`
        - Output: `(N, C, H, W)`
    .. _DropBlock: A regularization method for convolutional networks:
       https://arxiv.org/abs/1810.12890
    """

    def __init__(self, drop_prob, block_size):
        super(DropBlock2D, self).__init__()

        self.drop_prob = drop_prob
        self.block_size = block_size

    def forward(self, x):
        # shape: (bsize, channels, height, width)
        assert x.dim() == 4, \
            "Expected input with 4 dimensions (bsize, channels, height, width)"
        if not self.training or self.drop_prob == 0.:
            return x
        else:
            # get gamma value
            gamma = self._compute_gamma(x)
            # sample mask
            mask = (torch.rand(x.shape[0], *x.shape[2:]) < gamma).float()
            # place mask on input device
            mask = mask.to(x.device)
            # compute block mask
            block_mask = self._compute_block_mask(mask)
            # apply block mask
            out = x * block_mask[:, None, :, :]
            # scale output
            out = out * block_mask.numel() / block_mask.sum()

            return out

    def _compute_block_mask(self, mask):
        block_mask = F.max_pool2d(input=mask[:, None, :, :],
                                  kernel_size=(self.block_size, self.block_size),
                                  stride=(1, 1),
                                  padding=self.block_size // 2)
        if self.block_size % 2 == 0:
            block_mask = block_mask[:, :, :-1, :-1]
        block_mask = 1 - block_mask.squeeze(1)
        
        return block_mask

    def _compute_gamma(self, x):
        return self.drop_prob / (self.block_size ** 2)


class DropBlock3D(DropBlock2D):
    r"""Randomly zeroes 3D spatial blocks of the input tensor.
    An extension to the concept described in the paper
    `DropBlock: A regularization method for convolutional networks`_ ,
    dropping whole blocks of feature map allows to remove semantic
    information as compared to regular dropout.
    Args:
        drop_prob (float): probability of an element to be dropped.
        block_size (int): size of the block to drop
    Shape:
        - Input: `(N, C, D, H, W)`
        - Output: `(N, C, D, H, W)`
    .. _DropBlock: A regularization method for convolutional networks:
       https://arxiv.org/abs/1810.12890
    """

    def __init__(self, drop_prob, block_size):
        super(DropBlock3D, self).__init__(drop_prob, block_size)

    def forward(self, x):
        # shape: (bsize, channels, depth, height, width)

        assert x.dim() == 5, \
            "Expected input with 5 dimensions (bsize, channels, depth, height, width)"

        if not self.training or self.drop_prob == 0.:
            return x
        else:
            # get gamma value
            gamma = self._compute_gamma(x)
            # sample mask
            mask = (torch.rand(x.shape[0], *x.shape[2:]) < gamma).float()
            # place mask on input device
            mask = mask.to(x.device)
            # compute block mask
            block_mask = self._compute_block_mask(mask)
            # apply block mask
            out = x * block_mask[:, None, :, :, :]
            # scale output
            out = out * block_mask.numel() / block_mask.sum()

            return out

    def _compute_block_mask(self, mask):
        block_mask = F.max_pool3d(input=mask[:, None, :, :, :],
                                  kernel_size=(self.block_size, self.block_size, self.block_size),
                                  stride=(1, 1, 1),
                                  padding=self.block_size // 2)
        if self.block_size % 2 == 0:
            block_mask = block_mask[:, :, :-1, :-1, :-1]
        block_mask = 1 - block_mask.squeeze(1)
        
        return block_mask

    def _compute_gamma(self, x):
        return self.drop_prob / (self.block_size ** 3)