Apply SIoU on Bounding Box IoU metrics as default

- method metrics/bbox_iou
- applying it as default metric

utils/loss.py

@@ -138,7 +138,7 @@ def __call__(self, p, targets):  # predictions, targets
                 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)
+                iou = bbox_iou(pbox, tbox[i], SIoU=True).squeeze()  # iou(prediction, target)
                 lbox += (1.0 - iou).mean()  # iou loss
 
                 # Objectness

utils/metrics.py

@@ -219,7 +219,7 @@ def print(self):
             print(' '.join(map(str, self.matrix[i])))
 
 
-def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
+def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, eps=1e-7):
     # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)
 
     # Get the coordinates of bounding boxes
@@ -243,9 +243,28 @@ def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7
 
     # IoU
     iou = inter / union
-    if CIoU or DIoU or GIoU:
+    if CIoU or DIoU or GIoU or SIoU:
         cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1)  # convex (smallest enclosing box) width
         ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1)  # convex height
+         if SIoU:    # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
+            s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5
+            s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5
+            sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5) + eps
+            sin_alpha_1 = torch.abs(s_cw) / sigma
+            sin_alpha_2 = torch.abs(s_ch) / sigma
+            threshold = pow(2, 0.5) / 2
+            sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
+            # angle_cost = 1 - 2 * torch.pow( torch.sin(torch.arcsin(sin_alpha) - np.pi/4), 2)
+            # angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - np.pi / 2)
+            angle_cost = torch.sin(torch.arcsin(sin_alpha) * 2)
+            rho_x = (s_cw / (cw + eps)) ** 2
+            rho_y = (s_ch / (ch + eps)) ** 2
+            gamma = angle_cost - 2
+            distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
+            omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
+            omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
+            shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
+            return iou - 0.5 * (distance_cost + shape_cost)
         if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
             c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
             rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center dist ** 2

utils/segment/loss.py

@@ -62,7 +62,7 @@ def __call__(self, preds, targets, masks):  # predictions, targets, model
                 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)
+                iou = bbox_iou(pbox, tbox[i], SIoU=True).squeeze()  # iou(prediction, target)
                 lbox += (1.0 - iou).mean()  # iou loss
 
                 # Objectness