diff --git a/modules/dnn/src/layers/fully_connected_layer.cpp b/modules/dnn/src/layers/fully_connected_layer.cpp
index 2e08ed6d7e..c9baf79d00 100644
--- a/modules/dnn/src/layers/fully_connected_layer.cpp
+++ b/modules/dnn/src/layers/fully_connected_layer.cpp
@@ -449,7 +449,7 @@ public:
 
         InferenceEngine::Builder::Layer l = ieLayer;
         addConstantData("weights", wrapToInfEngineBlob(blobs[0], {(size_t)blobs[0].size[0], (size_t)blobs[0].size[1], 1, 1}, InferenceEngine::Layout::OIHW), l);
-        if (blobs.size() > 1)
+        if (bias)
             addConstantData("biases", wrapToInfEngineBlob(blobs[1], {(size_t)outNum}, InferenceEngine::Layout::C), l);
 
         return Ptr<BackendNode>(new InfEngineBackendNode(l));
diff --git a/modules/dnn/test/test_halide_layers.cpp b/modules/dnn/test/test_halide_layers.cpp
index d019b1d1ed..a85b3fa897 100644
--- a/modules/dnn/test/test_halide_layers.cpp
+++ b/modules/dnn/test/test_halide_layers.cpp
@@ -386,8 +386,11 @@ TEST_P(FullyConnected, Accuracy)
     bool hasBias = get<3>(GetParam());
     Backend backendId = get<0>(get<4>(GetParam()));
     Target targetId = get<1>(get<4>(GetParam()));
-    if (backendId == DNN_BACKEND_INFERENCE_ENGINE)
-        applyTestTag(CV_TEST_TAG_DNN_SKIP_IE);
+    if (backendId == DNN_BACKEND_INFERENCE_ENGINE && (targetId == DNN_TARGET_OPENCL_FP16 ||
+       (targetId == DNN_TARGET_MYRIAD && getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X))) {
+        applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16);
+        applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X);
+    }
 
     Mat weights(outChannels, inChannels * inSize.height * inSize.width, CV_32F);
     randu(weights, -1.0f, 1.0f);