目标检测5--旷视YOLOX算法介绍

时间:2022-10-12 09:54:14


欢迎访问个人网络日志????????知行空间????????


论文地址:http://arxiv.org/abs/2107.08430

代码:https://github.com/Megvii-BaseDetection/YOLOX

1.简介

2021年07月份,旷视的Zheng ZeSonttao Liu提交的论文中提出的Anchor Free检测算法。主要工作聚焦在a decoupled headlabel assigment strategy SimOTA。作者使用YOLOX获得了2021年CVPR Autonomous Driving领域Streaming Perception Challenge的第一名BaseDet

之前YOLO系列的论文自YoloV1后都是Anchor Based的,但自那之后如CornerNet/CenterNet/FCOSAnchor Free的算法不断进步,YoloX的作者再次尝试将Anchor Free的算法技巧应用到Yolo算法上。作者认为YoloV4/YoloV5属于优化过度的Anchor Based算法,因此其提出的YoloX算法主要与YoloV3做比较。YoloX中的使用的baselineYoloV3-SPP,YoloV3-SPP中作者引入了EMA权值更新, cosine lr schedule等策略。

2.YoloX所做的主要工作

2.1 分类/回归头解耦(Decoupled head)

R-CNN系列目标检测论文中,bounding box位置回归和物体类别判断都是分两个输出头来做的,而Yolo系列论文使用的Yolo Head都是在同个向量中通过共同的神经网络同时输出回归和类别信息。如下图1,在YoloX中作者重新使用了Decoupled Head,通过实验证明了其能提升检测的效果,

目标检测5--旷视YOLOX算法介绍

  • 1)加快收敛速度

目标检测5--旷视YOLOX算法介绍

  • 2)使用NMS FreeEnd2End Yolo时性能下降小。

目标检测5--旷视YOLOX算法介绍

2.2 SimOTA

Label Assignment时目标检测中的关键点,以往多是基于Max IoU来实现Anchor Box正负标签的判定,属于基于先验知识的静态匹配方式,因一张图像中目标的数量是有限的,因此会将大量的Anchor判定为negative,造成严重的类别不平衡问题。ATSS提出了自适应训练样本采样算法,自适应确定判断Anchor正负标签的IoU阈值。Label Assignment问题是结合Ground Truth Boxes给每个Anchor Box分配类别,然后得到全局最优的结果,这个问题正好满足二分图优化的模型,因此也有不少工作是基于匈牙利算法,最优路经传输(Optimal transport assignment)来做的。OTAYoloX作者2021年04月提交的论文中提出的方法,实现label的动态匹配。

advanced label assignment的四个要点

  • 1)loss/quality aware
  • 2)center prior
  • 3)dynamic number of positive anchors
  • 4) global view

YoloX作者指出通过Sinkhorn-Knopp算法求解OTA问题增加了约25%的训练时间,因此在YoloX中使用被称为SimOTAdynamic top-K算法求近似解。

SimOTA算法流程:

  • 1)先对每个prediction-gt pair计算代价cost

c o s t i j = L i j c l s + λ L i j r e g cost_{ij}=L^{cls}_{ij} + \lambda L^{reg}_{ij} costij=Lijcls+λLijreg

  • 2)对每个 g i g_i gi选择在一个中心范围内cost最小的top kprediction作为positive sample,其余作为negative samples,超参数k对不同的ground truth box取不同的值,其选择见作者在OTA论文中的介绍和这篇博客

源码分析:

参考mmdetectionSimOTA的实现,见mmdet/core/bbox/assigners/sim_ota_assigner.py

1.先调用get_in_gt_and_in_center_info方法
1.1prior center是否落在gt bboxes中?
1.2prior center是否落在gt box centers附近center_radius*stride_x/y矩形内?
2.初步判断priors哪些属于正样本is_in_gts_or_centers
3.bbox_overlaps将2的正样本与gt boxes分别计算IoU得iou_cost
4.binary_cross_entropy计算得cls_cost
5.cost_matrix:shape,num_posxgt_box_nums
6.dynamic_k_matching得到每个positive_prior对应的gt_box
匹配完成
class SimOTAAssigner(BaseAssigner):
    def __init__(self,):
     ...

    def _assign(self,
                pred_scores,
                priors,
                decoded_bboxes,
                gt_bboxes,
                gt_labels,
                gt_bboxes_ignore=None,
                eps=1e-7):
        """Assign gt to priors using SimOTA.
        Args:
            pred_scores (Tensor): Classification scores of one image,
                a 2D-Tensor with shape [num_priors, num_classes]
            priors (Tensor): All priors of one image, a 2D-Tensor with shape
                [num_priors, 4] in [cx, xy, stride_w, stride_y] format.
            decoded_bboxes (Tensor): Predicted bboxes, a 2D-Tensor with shape
                [num_priors, 4] in [tl_x, tl_y, br_x, br_y] format.
            gt_bboxes (Tensor): Ground truth bboxes of one image, a 2D-Tensor
                with shape [num_gts, 4] in [tl_x, tl_y, br_x, br_y] format.
            gt_labels (Tensor): Ground truth labels of one image, a Tensor
                with shape [num_gts].
            gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
                labelled as `ignored`, e.g., crowd boxes in COCO.
            eps (float): A value added to the denominator for numerical
                stability. Default 1e-7.
        Returns:
            :obj:`AssignResult`: The assigned result.
        """
        INF = 100000.0
        num_gt = gt_bboxes.size(0)
        num_bboxes = decoded_bboxes.size(0)

        # assign 0 by default
        assigned_gt_inds = decoded_bboxes.new_full((num_bboxes, ),
                                                   0,
                                                   dtype=torch.long)
        valid_mask, is_in_boxes_and_center = self.get_in_gt_and_in_center_info(
            priors, gt_bboxes)
        valid_decoded_bbox = decoded_bboxes[valid_mask]
        valid_pred_scores = pred_scores[valid_mask]
        num_valid = valid_decoded_bbox.size(0)

        if num_gt == 0 or num_bboxes == 0 or num_valid == 0:
            # No ground truth or boxes, return empty assignment
            max_overlaps = decoded_bboxes.new_zeros((num_bboxes, ))
            if num_gt == 0:
                # No truth, assign everything to background
                assigned_gt_inds[:] = 0
            if gt_labels is None:
                assigned_labels = None
            else:
                assigned_labels = decoded_bboxes.new_full((num_bboxes, ),
                                                          -1,
                                                          dtype=torch.long)
            return AssignResult(
                num_gt, assigned_gt_inds, max_overlaps, labels=assigned_labels)

        pairwise_ious = bbox_overlaps(valid_decoded_bbox, gt_bboxes)
        iou_cost = -torch.log(pairwise_ious + eps)

        gt_onehot_label = (
            F.one_hot(gt_labels.to(torch.int64),
                      pred_scores.shape[-1]).float().unsqueeze(0).repeat(
                          num_valid, 1, 1))

        valid_pred_scores = valid_pred_scores.unsqueeze(1).repeat(1, num_gt, 1)
        cls_cost = (
            F.binary_cross_entropy(
                valid_pred_scores.to(dtype=torch.float32).sqrt_(),
                gt_onehot_label,
                reduction='none',
            ).sum(-1).to(dtype=valid_pred_scores.dtype))

        cost_matrix = (
            cls_cost * self.cls_weight + iou_cost * self.iou_weight +
            (~is_in_boxes_and_center) * INF)

        matched_pred_ious, matched_gt_inds = \
            self.dynamic_k_matching(
                cost_matrix, pairwise_ious, num_gt, valid_mask)

        # convert to AssignResult format
        assigned_gt_inds[valid_mask] = matched_gt_inds + 1
        assigned_labels = assigned_gt_inds.new_full((num_bboxes, ), -1)
        assigned_labels[valid_mask] = gt_labels[matched_gt_inds].long()
        max_overlaps = assigned_gt_inds.new_full((num_bboxes, ),
                                                 -INF,
                                                 dtype=torch.float32)
        max_overlaps[valid_mask] = matched_pred_ious
        return AssignResult(
            num_gt, assigned_gt_inds, max_overlaps, labels=assigned_labels)

    def get_in_gt_and_in_center_info(self, priors, gt_bboxes):
        num_gt = gt_bboxes.size(0)

        repeated_x = priors[:, 0].unsqueeze(1).repeat(1, num_gt)
        repeated_y = priors[:, 1].unsqueeze(1).repeat(1, num_gt)
        repeated_stride_x = priors[:, 2].unsqueeze(1).repeat(1, num_gt)
        repeated_stride_y = priors[:, 3].unsqueeze(1).repeat(1, num_gt)

        # is prior centers in gt bboxes, shape: [n_prior, n_gt]
        l_ = repeated_x - gt_bboxes[:, 0]
        t_ = repeated_y - gt_bboxes[:, 1]
        r_ = gt_bboxes[:, 2] - repeated_x
        b_ = gt_bboxes[:, 3] - repeated_y

        deltas = torch.stack([l_, t_, r_, b_], dim=1)
        is_in_gts = deltas.min(dim=1).values > 0
        is_in_gts_all = is_in_gts.sum(dim=1) > 0

        # is prior centers in gt centers
        gt_cxs = (gt_bboxes[:, 0] + gt_bboxes[:, 2]) / 2.0
        gt_cys = (gt_bboxes[:, 1] + gt_bboxes[:, 3]) / 2.0
        ct_box_l = gt_cxs - self.center_radius * repeated_stride_x
        ct_box_t = gt_cys - self.center_radius * repeated_stride_y
        ct_box_r = gt_cxs + self.center_radius * repeated_stride_x
        ct_box_b = gt_cys + self.center_radius * repeated_stride_y

        cl_ = repeated_x - ct_box_l
        ct_ = repeated_y - ct_box_t
        cr_ = ct_box_r - repeated_x
        cb_ = ct_box_b - repeated_y

        ct_deltas = torch.stack([cl_, ct_, cr_, cb_], dim=1)
        is_in_cts = ct_deltas.min(dim=1).values > 0
        is_in_cts_all = is_in_cts.sum(dim=1) > 0

        # in boxes or in centers, shape: [num_priors]
        is_in_gts_or_centers = is_in_gts_all | is_in_cts_all

        # both in boxes and centers, shape: [num_fg, num_gt]
        is_in_boxes_and_centers = (
            is_in_gts[is_in_gts_or_centers, :]
            & is_in_cts[is_in_gts_or_centers, :])
        return is_in_gts_or_centers, is_in_boxes_and_centers

    def dynamic_k_matching(self, cost, pairwise_ious, num_gt, valid_mask):
        matching_matrix = torch.zeros_like(cost, dtype=torch.uint8)
        # select candidate topk ious for dynamic-k calculation
        candidate_topk = min(self.candidate_topk, pairwise_ious.size(0))
        # topk_ious shape: candidate_topk x num_gts
        topk_ious, _ = torch.topk(pairwise_ious, candidate_topk, dim=0)
        # calculate dynamic k for each gt
        # dynamic_ks shape: 1 x num_gts
        # dynamic k正是基于最少`candidate_topk`个iou求和计算出来的,因此是dynamic的
        # 每个 gt对应的topk是不一样的
        dynamic_ks = torch.clamp(topk_ious.sum(0).int(), min=1)
        for gt_idx in range(num_gt):
            _, pos_idx = torch.topk(
                cost[:, gt_idx], k=dynamic_ks[gt_idx], largest=False)
            matching_matrix[:, gt_idx][pos_idx] = 1

        """
        以上生成的`matching_matrix`有可能1个`prior`对应多个`gt_boxes`,还需以下处理
        从1个`prior`对应的多个`gt_boxes`选`cost`最小的那个作为`gt_box`
        """
        del topk_ious, dynamic_ks, pos_idx
        # prior_match_gt_mask shape like (num_priors,)
        prior_match_gt_mask = matching_matrix.sum(1) > 1
        if prior_match_gt_mask.sum() > 0:
            cost_min, cost_argmin = torch.min(
                cost[prior_match_gt_mask, :], dim=1)
            matching_matrix[prior_match_gt_mask, :] *= 0
            matching_matrix[prior_match_gt_mask, cost_argmin] = 1
        # get foreground mask inside box and center prior
        fg_mask_inboxes = matching_matrix.sum(1) > 0
        valid_mask[valid_mask.clone()] = fg_mask_inboxes

        matched_gt_inds = matching_matrix[fg_mask_inboxes, :].argmax(1)
        matched_pred_ious = (matching_matrix *
                             pairwise_ious).sum(1)[fg_mask_inboxes]
        return matched_pred_ious, matched_gt_inds

2.3 End2End Yolo(NMS Free)

2020年12月份,旷视的Jianfeng Wang等提交的论文End-to-End Object Detection with Fully Convolutional Network 提出了不需要使用极大值抑制做后处理的检测方法,其改进了label assigment,将以往one2many的标签分配方式改成了one2one的方式,更多介绍可参考论文作者知乎上的文章2021年01月份阿里的Qiang Zhou等提交的论文[Object Detection Made Simpler by Eliminating Heuristic NMS](https://arxiv.org/abs/2101.11782)中也使用one2one的标签分配方式实现了NMS Free的目标检测算法,YoloX参考以上方法实现End2End训练得到如下表灰色的实验结果,可以看到对性能和准确率都有一定的影响:

目标检测5--旷视YOLOX算法介绍

最近聚焦在研究label assignment,因此这块NMS Free还没来得及看源码,先挖个坑。NMS Free其实也非常有意义,因为NMS存在,在边缘设备部署模型时,后处理部分不能像模型本身能放NPU上加速计算,故需在CPU上运算。

2.4 其他

  • 数据增强方法

    • Mosaic:YoloV5作者在ultralytics-YOLOv3中提出的

    • MixUp2018年mixup: Beyond empirical risk minimization论文中提出,最早用于图像分类,自BoF后用于目标检测的数据增强

目标检测5--旷视YOLOX算法介绍

  • Anchor Free: 做法类似于FCOS,每个feature map cell只预测一个输出框,相当于Anchor Number=1。同时为了得到更多的正样本,将Feature Mapcell落在目标中心附近一定范围的点都当作正样本,即Multiple Positive Sample

欢迎访问个人网络日志????????知行空间????????


参考资料