diff --git a/modules/dnn/include/opencv2/dnn/dnn.hpp b/modules/dnn/include/opencv2/dnn/dnn.hpp
index 680e7d54d195bb0da8a8aa787f7cb8cf371ed614..d11b3a5c460ed2a40fc68623745af93ad469cd55 100644
--- a/modules/dnn/include/opencv2/dnn/dnn.hpp
+++ b/modules/dnn/include/opencv2/dnn/dnn.hpp
@@ -535,6 +535,11 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
         /** @brief Returns indexes of layers with unconnected outputs.
          */
         CV_WRAP std::vector<int> getUnconnectedOutLayers() const;
+
+        /** @brief Returns names of layers with unconnected outputs.
+         */
+        CV_WRAP std::vector<String> getUnconnectedOutLayersNames() const;
+
         /** @brief Returns input and output shapes for all layers in loaded model;
          *  preliminary inferencing isn't necessary.
          *  @param netInputShapes shapes for all input blobs in net input layer.
diff --git a/modules/dnn/src/dnn.cpp b/modules/dnn/src/dnn.cpp
index e48659e31c9cbdc1f97143c3aece5da7725a445d..16fb06cca551e92e5ba810f074a21e9c110d34f7 100644
--- a/modules/dnn/src/dnn.cpp
+++ b/modules/dnn/src/dnn.cpp
@@ -2789,6 +2789,18 @@ std::vector<int> Net::getUnconnectedOutLayers() const
     return layersIds;
 }
 
+std::vector<String> Net::getUnconnectedOutLayersNames() const
+{
+    std::vector<int> ids = getUnconnectedOutLayers();
+    const size_t n = ids.size();
+    std::vector<String> names(n);
+    for (size_t i = 0; i < n; ++i)
+    {
+        names[i] = impl->layers[ids[i]].name;
+    }
+    return names;
+}
+
 void Net::getLayersShapes(const ShapesVec& netInputShapes,
                           std::vector<int>& layersIds,
                           std::vector<ShapesVec>& inLayersShapes,
diff --git a/samples/dnn/object_detection.cpp b/samples/dnn/object_detection.cpp
index 161f7434f8cebdcea56eb043e3daac4c68cfffb4..eddac3a14344ac6bdcc126a81ea2adae2c85834c 100644
--- a/samples/dnn/object_detection.cpp
+++ b/samples/dnn/object_detection.cpp
@@ -86,6 +86,7 @@ int main(int argc, char** argv)
     Net net = readNet(parser.get<String>("model"), parser.get<String>("config"), parser.get<String>("framework"));
     net.setPreferableBackend(parser.get<int>("backend"));
     net.setPreferableTarget(parser.get<int>("target"));
+    std::vector<String> outNames = net.getUnconnectedOutLayersNames();
 
     // Create a window
     static const std::string kWinName = "Deep learning object detection in OpenCV";
@@ -125,7 +126,7 @@ int main(int argc, char** argv)
             net.setInput(imInfo, "im_info");
         }
         std::vector<Mat> outs;
-        net.forward(outs, getOutputsNames(net));
+        net.forward(outs, outNames);
 
         postprocess(frame, outs, net);
 
@@ -265,17 +266,3 @@ void callback(int pos, void*)
 {
     confThreshold = pos * 0.01f;
 }
-
-std::vector<String> getOutputsNames(const Net& net)
-{
-    static std::vector<String> names;
-    if (names.empty())
-    {
-        std::vector<int> outLayers = net.getUnconnectedOutLayers();
-        std::vector<String> layersNames = net.getLayerNames();
-        names.resize(outLayers.size());
-        for (size_t i = 0; i < outLayers.size(); ++i)
-            names[i] = layersNames[outLayers[i] - 1];
-    }
-    return names;
-}
diff --git a/samples/dnn/object_detection.py b/samples/dnn/object_detection.py
index 76c33f8e3b62140bd8ae1d2f017bb1f32a0ca6f1..b97d8df66946f3d90b549ee235c914c6c7c15b85 100644
--- a/samples/dnn/object_detection.py
+++ b/samples/dnn/object_detection.py
@@ -78,14 +78,11 @@ if args.classes:
 net = cv.dnn.readNet(args.model, args.config, args.framework)
 net.setPreferableBackend(args.backend)
 net.setPreferableTarget(args.target)
+outNames = net.getUnconnectedOutLayersNames()
 
 confThreshold = args.thr
 nmsThreshold = args.nms
 
-def getOutputsNames(net):
-    layersNames = net.getLayerNames()
-    return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]
-
 def postprocess(frame, outs):
     frameHeight = frame.shape[0]
     frameWidth = frame.shape[1]
@@ -213,7 +210,7 @@ while cv.waitKey(1) < 0:
     if net.getLayer(0).outputNameToIndex('im_info') != -1:  # Faster-RCNN or R-FCN
         frame = cv.resize(frame, (inpWidth, inpHeight))
         net.setInput(np.array([[inpHeight, inpWidth, 1.6]], dtype=np.float32), 'im_info')
-    outs = net.forward(getOutputsNames(net))
+    outs = net.forward(outNames)
 
     postprocess(frame, outs)