论文地址：https://arxiv.org/abs/2110.13389

文章解读：提升小目标检测新的包围框相似度度量：Normalized Gaussian Wasserstein Distance_athrunsunny的博客-CSDN博客

代码修改：

utils/metrics.py

def wasserstein_loss(pred, target, eps=1e-7, constant=12.8):
    """Implementation of paper `A Normalized Gaussian Wasserstein Distance for
    Tiny Object Detection <https://arxiv.org/abs/2110.13389>.
    Args:
        pred (Tensor): Predicted bboxes of format (cx, cy, w, h),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).
    Return:
        Tensor: Loss tensor.
    """
    center1 = pred[:, :2]
    center2 = target[:, :2]
    whs = center1[:, :2] - center2[:, :2]
    center_distance = whs[:, 0] * whs[:, 0] + whs[:, 1] * whs[:, 1] + eps

    w1 = pred[:, 2] + eps
    h1 = pred[:, 3] + eps
    w2 = target[:, 2] + eps
    h2 = target[:, 3] + eps

    wh_distance = ((w1 - w2) ** 2 + (h1 - h2) ** 2) / 4
    wasserstein_2 = center_distance + wh_distance
    return torch.exp(-torch.sqrt(wasserstein_2) / constant)

在utils/loss.py中添加 

from utils.metrics import bbox_iou, box_iou, wasserstein_loss

 在ComputeLoss函数中做如下修改：

class ComputeLoss:
    sort_obj_iou = False

    # Compute losses
    def __init__(self, model, autobalance=False):
        device = next(model.parameters()).device  # get model device
        h = model.hyp  # hyperparameters

        # Define criteria
        BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
        BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))

        # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
        self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0))  # positive, negative BCE targets

        # Focal loss
        g = h['fl_gamma']  # focal loss gamma
        if g > 0:
            BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)

        m = de_parallel(model).model[-1]  # Detect() module
        self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02])  # P3-P7
        self.ssi = list(m.stride).index(16) if autobalance else 0  # stride 16 index
        self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
        self.na = m.na  # number of anchors
        self.nc = m.nc  # number of classes
        self.nl = m.nl  # number of layers
        self.anchors = m.anchors
        self.device = device

    def __call__(self, p, targets):  # predictions, targets
        lcls = torch.zeros(1, device=self.device)  # class loss
        lbox = torch.zeros(1, device=self.device)  # box loss
        lobj = torch.zeros(1, device=self.device)  # object loss
        tcls, tbox, indices, anchors = self.build_targets(p, targets)  # targets

        # Losses
        for i, pi in enumerate(p):  # layer index, layer predictions
            b, a, gj, gi = indices[i]  # image, anchor, gridy, gridx
            tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device)  # target obj

            n = b.shape[0]  # number of targets
            if n:
                # pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1)  # faster, requires torch 1.8.0
                pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1)  # target-subset of predictions

                # Regression
                pxy = pxy.sigmoid() * 2 - 0.5
                pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
                pbox = torch.cat((pxy, pwh), 1)  # predicted box
                iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze()  # iou(prediction, target)
                # lbox += (1.0 - iou).mean()  # iou loss
                #
                # # Objectness
                # iou = iou.detach().clamp(0).type(tobj.dtype)

                nwd_ratio = 0.5  # 平衡nwd和原始iou的权重 
                nwd = wasserstein_loss(pbox, tbox[i]).squeeze()
                lbox += (1 - nwd_ratio) * (1.0 - nwd).mean() + nwd_ratio * (1.0 - iou).mean()  # iou loss

                # Objectness
                iou = (iou.detach() * nwd_ratio + nwd.detach() * (1 - nwd_ratio)).clamp(0, 1).type(tobj.dtype)

                if self.sort_obj_iou:
                    j = iou.argsort()
                    b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j]
                if self.gr < 1:
                    iou = (1.0 - self.gr) + self.gr * iou
                tobj[b, a, gj, gi] = iou  # iou ratio

                # Classification
                if self.nc > 1:  # cls loss (only if multiple classes)
                    t = torch.full_like(pcls, self.cn, device=self.device)  # targets
                    t[range(n), tcls[i]] = self.cp
                    lcls += self.BCEcls(pcls, t)  # BCE

                # Append targets to text file
                # with open('targets.txt', 'a') as file:
                #     [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]

            obji = self.BCEobj(pi[..., 4], tobj)
            lobj += obji * self.balance[i]  # obj loss
            if self.autobalance:
                self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()

        if self.autobalance:
            self.balance = [x / self.balance[self.ssi] for x in self.balance]
        lbox *= self.hyp['box']
        lobj *= self.hyp['obj']
        lcls *= self.hyp['cls']
        bs = tobj.shape[0]  # batch size

        return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()

    def build_targets(self, p, targets):
        # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
        na, nt = self.na, targets.shape[0]  # number of anchors, targets
        tcls, tbox, indices, anch = [], [], [], []
        gain = torch.ones(7, device=self.device)  # normalized to gridspace gain
        ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
        targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2)  # append anchor indices

        g = 0.5  # bias
        off = torch.tensor(
            [
                [0, 0],
                [1, 0],
                [0, 1],
                [-1, 0],
                [0, -1],  # j,k,l,m
                # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
            ],
            device=self.device).float() * g  # offsets

        for i in range(self.nl):
            anchors, shape = self.anchors[i], p[i].shape
            gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]]  # xyxy gain

            # Match targets to anchors
            t = targets * gain  # shape(3,n,7)
            if nt:
                # Matches
                r = t[..., 4:6] / anchors[:, None]  # wh ratio
                j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t']  # compare
                # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
                t = t[j]  # filter

                # Offsets
                gxy = t[:, 2:4]  # grid xy
                gxi = gain[[2, 3]] - gxy  # inverse
                j, k = ((gxy % 1 < g) & (gxy > 1)).T
                l, m = ((gxi % 1 < g) & (gxi > 1)).T
                j = torch.stack((torch.ones_like(j), j, k, l, m))
                t = t.repeat((5, 1, 1))[j]
                offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
            else:
                t = targets[0]
                offsets = 0

            # Define
            bc, gxy, gwh, a = t.chunk(4, 1)  # (image, class), grid xy, grid wh, anchors
            a, (b, c) = a.long().view(-1), bc.long().T  # anchors, image, class
            gij = (gxy - offsets).long()
            gi, gj = gij.T  # grid indices

            # Append
            indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1)))  # image, anchor, grid
            tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
            anch.append(anchors[a])  # anchors
            tcls.append(c)  # class

        return tcls, tbox, indices, anch