changed incremental novelty semseg to use features stored in a member variable (aim: set arbitrary region, e.g. rects, as pseudo-novel regions)

semseg/SemSegNovelty.cpp

@@ -521,17 +521,18 @@ void SemSegNovelty::semanticseg ( CachedExample *ce, NICE::Image & segresult, NI
     return;
   }
 
-  MultiChannelImageT<double> feats;
+ // MultiChannelImageT<double> m_CurrentImageFeatures;
 
   // extract features
-  featExtract->getFeats ( img, feats );
-  featdim = feats.channels();
-  feats.addChannel(featdim);
+  m_CurrentImageFeatures.freeData();
+  featExtract->getFeats ( img, m_CurrentImageFeatures );
+  featdim = m_CurrentImageFeatures.channels();
+  m_CurrentImageFeatures.addChannel(featdim);
 
   for (int c = 0; c < featdim; c++)
   {
-    ImageT<double> tmp = feats[c];
-    ImageT<double> tmp2 = feats[c+featdim];
+    ImageT<double> tmp = m_CurrentImageFeatures[c];
+    ImageT<double> tmp2 = m_CurrentImageFeatures[c+featdim];
 
     NICE::FilterT<double, double, double>::gradientStrength (tmp, tmp2);
   }
@@ -540,7 +541,7 @@ void SemSegNovelty::semanticseg ( CachedExample *ce, NICE::Image & segresult, NI
   // compute integral images
   for ( int c = 0; c < featdim; c++ )
   {
-    feats.calcIntegral ( c );
+    m_CurrentImageFeatures.calcIntegral ( c );
   }
   
   timer.stop();
@@ -552,7 +553,7 @@ void SemSegNovelty::semanticseg ( CachedExample *ce, NICE::Image & segresult, NI
   //in all other settings, such as active sem seg in general, we do this within the novelty-computation-methods
   if ( classifier == NULL )
   {
-    this->computeClassificationResults( feats, segresult, probabilities, xsize, ysize, featdim);
+    this->computeClassificationResults( m_CurrentImageFeatures, segresult, probabilities, xsize, ysize, featdim);
   }
 //   timer.stop();
 //   
@@ -565,38 +566,38 @@ void SemSegNovelty::semanticseg ( CachedExample *ce, NICE::Image & segresult, NI
   {
     case GPVARIANCE:
     {
-         this->computeNoveltyByVariance( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByVariance( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;
     }
     case GPUNCERTAINTY:
     {
-         this->computeNoveltyByGPUncertainty( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByGPUncertainty( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;         
     }
     case GPMINMEAN:
     {
          std::cerr << "compute novelty using the minimum mean" << std::endl;
-         this->computeNoveltyByGPMean( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByGPMean( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;         
     }
     case GPMEANRATIO:
     {
-         this->computeNoveltyByGPMeanRatio( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByGPMeanRatio( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;         
     }
     case GPWEIGHTALL:
     {
-         this->computeNoveltyByGPWeightAll( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByGPWeightAll( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;         
     }
     case GPWEIGHTRATIO:
     {
-         this->computeNoveltyByGPWeightRatio( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByGPWeightRatio( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;         
     }    
     case RANDOM:
     {
-         this->computeNoveltyByRandom( noveltyImage, feats, segresult, probabilities, xsize, ysize,  featdim );
+         this->computeNoveltyByRandom( noveltyImage, m_CurrentImageFeatures, segresult, probabilities, xsize, ysize,  featdim );
          break;               
     }
     default:
@@ -724,35 +725,40 @@ void SemSegNovelty::semanticseg ( CachedExample *ce, NICE::Image & segresult, NI
         //current most novel region of the image has "higher" novelty score then previous most novel region of all test images worked on so far
         // -> save new important features of this region
         Examples examples;
+
         for ( int y = 0; y < ysize; y += testWSize )
         {
           for ( int x = 0; x < xsize; x += testWSize)
           {
-            if(mask(x,y) == maxUncertRegion)
-            {
-              int classnoTmp = labels(x,y);
-              if ( forbidden_classesActiveLearning.find(classnoTmp) != forbidden_classesActiveLearning.end() )
-                continue;
-              
-              Example example(NULL, x, y);
-              example.vec = NULL;
-              example.svec = new SparseVector ( featdim );
-              
-              for ( int f = 0; f < featdim; f++ )
+              if(mask(x,y) == maxUncertRegion)
               {
-                double val = feats.getIntegralValue ( x - whs, y - whs, x + whs, y + whs, f );
-                if ( val > 1e-10 )
-                  ( *example.svec ) [f] = val;
+                  if ( forbidden_classesActiveLearning.find(classnoTmp) != forbidden_classesActiveLearning.end() )
+                      continue;
+                  int classnoTmp = labels(x,y);
+                  Example t_Example(NULL, x, y);
+                  t_Example.vec = NULL;
+                  t_Example.svec = new SparseVector ( featdim );
+                  for ( int f = 0; f < featdim; f++ )
+                  {
+//                      double val =  ( *example.svec ) [f];
+                       double val = m_CurrentImageFeatures.getIntegralValue ( x - whs, y - whs, x + whs, y + whs, f );
+                    if ( val > 1e-10 )
+                      ( *t_Example.svec ) [f] = val;
+                  }
+                  examples.push_back ( pair<int, Example> ( classnoTmp, t_Example ) );
               }
-              example.svec->normalize();
-              examples.push_back ( pair<int, Example> ( classnoTmp, example ) );
-            }
           }
         }
         
         if(examples.size() > 0)
         {
           std::cerr << "found " << examples.size() << " new examples in the queried region" << std::endl << std::endl;
+          // sauber aufräumen
+          for( int i=0; i< newTrainExamples.size(); i++)
+          {
+              delete newTrainExamples.at(i).second.svec;
+              newTrainExamples.at(i).second.svec = NULL;
+          }
           newTrainExamples.clear();
           newTrainExamples = examples;
           globalMaxUncert = maxNoveltyScore;

semseg/SemSegNovelty.h

@@ -135,7 +135,8 @@ class SemSegNovelty : public SemanticSegmentation
     
     //! current examples for most uncertain region
     Examples newTrainExamples;    
-    
+
+    NICE::MultiChannelImageT<double> m_CurrentImageFeatures;
     ///////////////////////////////
     //     SEGMENTATION STUFF    //
     ///////////////////////////////