论文笔记+源码 DETR:End-to-End Object Detection with Transformers

〇、本论文需要有的基础知识

  • 目标检测:了解传统目标检测的基本技术路线(如anchor-based、非最极大值抑制、one-stage、two-stage),大致了解近两年的SOTA方法(如Faster-RCNN)
  • Transformer:了解Transformer的机制,知道self-attention机制
  • 二分图匹配:了解图论中的二分图匹配,知道匈牙利算法
  •  


一、 摘要核心点

1. 相比传统路线:去掉了很多手工设计模块(hand-designed):如非极大值抑制、anchor的设计
这些手工设计的模块里均为人为对task先验知识的一定程度上的“先验的编码(encode)”

2. DETR核心内容
a set-based global loss → forces unique predictions via: 
(a) bipartite matching, and 
(b) a transformer encoder-decoder architecture.(本文用的Transformer网络是non-autoregressive非自回归的)

关于非自回归的介绍可以参考https://zhuanlan.zhihu.com/p/82892975

3. DETR能做到的事
· 输入: a fixed small set of learned objects queries
· DETR输出:

(a) the relations of the objects
(b) the global image context to directly output the final set of prediction in parallel

4. 流程架构示意图:

论文笔记+源码 DETR:End-to-End Object Detection with Transformers

更细节一些的流程架构示意图↓:

论文笔记+源码 DETR:End-to-End Object Detection with Transformers

 

二、 正文

1. 首先定性object detection问题为set of prediction

2. 整个网络设计是端到端(end-to-end)的,然后用一个“集合”损失函数(set loss function)来训练,这个损失函数描述预测框和ground-truth框之间的二分图匹配( performs bipartite matching between predicted and ground-truth objects)来训练

3. DETR仅仅是架构上的创新,并没有创新独有的层(就好像resnet创新了跳连,DETR没有在layer这个层面进行创新)

4. DETR用的“匹配”损失函数(matching loss function)将预测框“一一分配”给ground-truth框(uniquely assigns a prediction to a ground truth object,这里的“一一分配”正是bipartite matching的本身含义);而且能保证对预测对象的排列顺序保持不变(这也是用二分图匹配建模的原因,这里特指无向二分图)(uniquely assigns a prediction to a ground truth object)→这是能够并行化预测的一个原因

“matching”这里是图论里的概念,可以参考https://www.renfei.org/blog/bipartite-matching.html

5. 对于建模为“Set Prediction”(“集合”预测)的考虑:

通常“集合”预测任务是一种多标签分类问题。多标签分类问题的解决方法通常是“one-vs-rest”(“一对多”,one-vs-rest,又称one-vs-all, 这里指的是将label的类别作为“一”,将其余类别当做一个整体作为“多”,进行训练),这种方法不适用于“元素”间有底层关系结构的情况(“元素”e.g.几乎一模一样的预测框)(does not apply to problems such as detection where there is an underlying structure between elements (i.e., near-identical boxes)。这个方法会导致大量几乎一样的结果的情况(near-duplicates),传统的目标检测方法会用后处理(如非极大值抑制)来解决这个问题(成堆的近乎一样的预测结果),但是如果是建模为set prediction就不用这些后处理。set prediction需要在全局上有个策略来对这些“元素”之间的关系建模,来避免预测过多的无用、复制的结果造成冗余。

6. 对于采用“Bipartite Matching”(二分图匹配)作为“预测值→ground-truth值”的损失函数的考虑:

在Set Prediction问题中,损失函数必须满足“预测顺序不变性”(invariant by a permutation of the predictions,即预测值/框的顺序不能影响损失值),而二分图匹配——这里特指的是“无向”二分图匹配将“预测值→ground-truth值”的关系建模为了一个无向二分图,这种图的“匹配”不存在顺序问题。特别地,用“匈牙利算法”来求解二分图匹配问题。

· “Bipartite Matching”(二分图匹配)(1)能保证预测顺序不变性”; (2)能保证两者间的“一一匹配”

7. 对于大物体的预测更准确:

文章中说“a result likely enabled by the non-local computations of the transformer”,这里的“non-local computations”指的是Non-local Neural Networkshttps://arxiv.org/pdf/1711.07971.pdf)这篇文章中的Non-local概念。

non-local computations指的是计算“非局部”感受野上的信息,可以参考https://zhuanlan.zhihu.com/p/33345791

三、结果

 

四、源码讨论

为了防止后面代码项目有改动,我摘出来写本文时候(2020.06.18)的最新的一次提交(1fcfc65)来做部分源码说明

DETR网络结构一览:

class DETR(nn.Module):
    """ This is the DETR module that performs object detection """
    def __init__(self, backbone, transformer, num_classes, num_queries, aux_loss=False):
        """ Initializes the model.
        Parameters:
            backbone: torch module of the backbone to be used. See backbone.py
            transformer: torch module of the transformer architecture. See transformer.py
            num_classes: number of object classes
            num_queries: number of object queries, ie detection slot. This is the maximal number of objects
                         DETR can detect in a single image. For COCO, we recommend 100 queries.
            aux_loss: True if auxiliary decoding losses (loss at each decoder layer) are to be used.
        """
        super().__init__()
        self.num_queries = num_queries
        self.transformer = transformer
        hidden_dim = transformer.d_model
        self.class_embed = nn.Linear(hidden_dim, num_classes + 1)
        self.bbox_embed = MLP(hidden_dim, hidden_dim, 4, 3)
        self.query_embed = nn.Embedding(num_queries, hidden_dim)
        self.input_proj = nn.Conv2d(backbone.num_channels, hidden_dim, kernel_size=1)
        self.backbone = backbone
        self.aux_loss = aux_loss

    def forward(self, samples: NestedTensor):
        """ The forward expects a NestedTensor, which consists of:
               - samples.tensor: batched images, of shape [batch_size x 3 x H x W]
               - samples.mask: a binary mask of shape [batch_size x H x W], containing 1 on padded pixels
            It returns a dict with the following elements:
               - "pred_logits": the classification logits (including no-object) for all queries.
                                Shape= [batch_size x num_queries x (num_classes + 1)]
               - "pred_boxes": The normalized boxes coordinates for all queries, represented as
                               (center_x, center_y, height, width). These values are normalized in [0, 1],
                               relative to the size of each individual image (disregarding possible padding).
                               See PostProcess for information on how to retrieve the unnormalized bounding box.
               - "aux_outputs": Optional, only returned when auxilary losses are activated. It is a list of
                                dictionnaries containing the two above keys for each decoder layer.
        """
        if not isinstance(samples, NestedTensor):
            samples = nested_tensor_from_tensor_list(samples)
        features, pos = self.backbone(samples) # backbone是一个CNN用于特征提取

        src, mask = features[-1].decompose() #??
        assert mask is not None
        hs = self.transformer(self.input_proj(src), mask, self.query_embed.weight, pos[-1])[0]  # 这里是吧features的其中一部分信息作为src传进Transformer,input_proj是一个卷积层,用来收缩输入的维度,把维度控制到d_model的尺寸(model dimension)

        outputs_class = self.class_embed(hs)  # 为了把Transformer应用于目标检测问题上,作者引入了“类别嵌入网络”和“框嵌入网络”
        outputs_coord = self.bbox_embed(hs).sigmoid()  # 在框嵌入后加入一层sigmoid输出框坐标(原论文中提到是四点坐标,但是要考虑到原图片的尺寸)
        out = {'pred_logits': outputs_class[-1], 'pred_boxes': outputs_coord[-1]}
        if self.aux_loss:
            out['aux_outputs'] = self._set_aux_loss(outputs_class, outputs_coord)
        return out

    @torch.jit.unused
    def _set_aux_loss(self, outputs_class, outputs_coord):
        # this is a workaround to make torchscript happy, as torchscript
        # doesn't support dictionary with non-homogeneous values, such
        # as a dict having both a Tensor and a list.
        return [{'pred_logits': a, 'pred_boxes': b}
                for a, b in zip(outputs_class[:-1], outputs_coord[:-1])]

TBC.(没写完的部分最近会补上,毕竟我也是边看边学然后记下来的……)

上一篇:mask-rcnn代码解读(四):rpn_feature_maps数据的处理


下一篇:第三章 自己动手写区块链之交易