Release deepmac changes to CenterNet proto.

PiperOrigin-RevId: 370255238

research/object_detection/protos/center_net.proto

@@ -347,6 +347,59 @@ message CenterNet {
   optional TemporalOffsetEstimation temporal_offset_task = 12;
 
 
+  // Mask prediction support using DeepMAC. See https://arxiv.org/abs/2104.00613
+  message DeepMACMaskEstimation {
+    // The loss used for penalizing mask predictions.
+    optional ClassificationLoss classification_loss = 1;
+
+    // Weight of mask prediction loss
+    optional float task_loss_weight = 2 [default = 1.0];
+
+    // The dimension of the per-instance embedding.
+    optional int32 dim = 3 [default = 256];
+
+    // The dimension of the per-pixel embedding
+    optional int32 pixel_embedding_dim = 4 [default=16];
+
+    // If set, masks are only kept for classes listed here. Masks are deleted
+    // for all other classes. Note that this is only done at training time, eval
+    // behavior is unchanged.
+    repeated int32 allowed_masked_classes_ids = 5;
+
+    // The size of cropped pixel embedding that goes into the 2D mask prediction
+    // network (RoI align).
+    optional int32 mask_size = 6 [default=32];
+
+    // If set to a positive value, we subsample instances by this amount to
+    // save memory during training.
+    optional int32 mask_num_subsamples = 67[default=-1];
+
+    // Whether or not to use (x, y) coordinates as input to mask net.
+    optional bool use_xy = 8 [default=true];
+
+    // Defines the kind of architecture we want to use for mask network.
+    optional string network_type = 9 [default="hourglass52"];
+
+    // Whether or not we want to use instance embedding in mask network.
+    optional bool use_instance_embedding = 10 [default=true];
+
+    // Number of channels in the inital block of the mask prediction network.
+    optional int32 num_init_channels = 11 [default=64];
+
+    // Whether or not to predict masks at full resolution. If true, we predict
+    // masks at the resolution of the output stride. Otherwise, masks are
+    // predicted at resolution defined by mask_size
+    optional bool predict_full_resolution_masks = 12 [default=false];
+
+    // If predict_full_resolution_masks is set, this parameter controls the size
+    // of cropped masks returned by post-process. To be compatible with the rest
+    // of the API, masks are always cropped and resized according to detected
+    // boxes in postprocess.
+    optional int32 postprocess_crop_size = 13 [default=256];
+  }
+
+  optional DeepMACMaskEstimation deepmac_mask_estimation = 14;
+
   // CenterNet does not apply conventional post processing operations such as
   // non max suppression as it applies a max-pool operator on box centers.
   // However, in some cases we observe the need to remove duplicate predictions