Hypercolumn technique

Hypercolumn is a technique that performs the classification on pixels using hyper column. That is, each image given as an input to the model has a hyper column vector. These hyper vectors hold all the activation features of that pixel in the convolutional model. Thus, instead of deciding according to the pixel value in the final layer of the convolutional model in the classification process, it chooses the most efficient one by examining all the features in the hyper column vector. Thus, with this technique, the spatial location information of the most efficient feature is brought from the previous layers, and contributing to the classification process.

Basically, the essence of the Hypercolumn technique is based on heat maps. After the convolution layers of the model, this technique uses bilinear interpolation and creates a transition feature value using two feature values with Bilinear interpolation. In other words, bilinear interpolation creates a smooth transition value between two feature values. In this way, feature maps extracted from other layers of the model are added and it is processed with the sigmoid function. Heat maps extracted from the model are then combined to produce possible output values. This joining is done by the “Concatenate” function in the hypercolumn technique. In addition, with the Upsampling2D function, it keeps the neighboring pixel values of a pixel and transfers it to the required places (Toğaçar, Ergen & Cömert, 2020a; Toğaçar, Ergen & Cömert, 2020b).