diff --git a/modules/dnn/perf/perf_convolution.cpp b/modules/dnn/perf/perf_convolution.cpp
index bb890c6a00..99f425b712 100644
--- a/modules/dnn/perf/perf_convolution.cpp
+++ b/modules/dnn/perf/perf_convolution.cpp
@@ -744,7 +744,8 @@ static const ConvParam_t testConvolutionConfigs[] = {
     /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 4, 1, 1}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 864.},
     /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 96, 1, 1}}, 4, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 772.},
     /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 8, 1, 1}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 544.},
-    /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 32, 1, 1}}, 8, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 520.}
+    /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 32, 1, 1}}, 8, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 520.},
+    /* GFLOPS 0.472 x 1 = 0.472 */ {{5, 5}, {{1, 32, 96, 96}}, 32, 32, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 472154112.}
 };
 struct ConvParamID
 {
diff --git a/modules/dnn/src/layers/cpu_kernels/convolution.cpp b/modules/dnn/src/layers/cpu_kernels/convolution.cpp
index c76b3494e2..68777ff65e 100644
--- a/modules/dnn/src/layers/cpu_kernels/convolution.cpp
+++ b/modules/dnn/src/layers/cpu_kernels/convolution.cpp
@@ -1290,7 +1290,7 @@ void runFastConv(InputArray _input, OutputArray _output, const Ptr<FastConv>& co
     else
         Kg_nblocks = 1;
 
-    bool separateIm2col = fast_1x1 || stripes_per_plane == 1;
+    bool separateIm2col = (fast_1x1 || stripes_per_plane == 1) && conv->conv_type != CONV_TYPE_DEPTHWISE_REMAIN;
 
     int Kstripes = Kg_nblocks * stripes_per_plane;
     int nsubtasks = N * ngroups * Kstripes;