$ N^4 $-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
This work addresses image processing challenges for computer vision applications, but it is incremental as it builds on existing neural network and nearest neighbor methods.
The paper tackles the problem of difficult image processing operations like natural edge detection and thin object segmentation by proposing a new architecture that combines convolutional neural networks with nearest neighbor search to address underfitting. The approach matches or exceeds state-of-the-art performance on three challenging benchmarks.
We propose a new architecture for difficult image processing operations, such as natural edge detection or thin object segmentation. The architecture is based on a simple combination of convolutional neural networks with the nearest neighbor search. We focus our attention on the situations when the desired image transformation is too hard for a neural network to learn explicitly. We show that in such situations, the use of the nearest neighbor search on top of the network output allows to improve the results considerably and to account for the underfitting effect during the neural network training. The approach is validated on three challenging benchmarks, where the performance of the proposed architecture matches or exceeds the state-of-the-art.