CNN-aware Binary Map for General Semantic Segmentation
It addresses the problem of general semantic segmentation for computer vision applications, which is incremental as it builds on CNN features but claims to be the first for general use beyond limited datasets like PASCAL VOC.
The paper tackles general semantic segmentation by using binary encoding of CNN features to create visually and semantically coherent segments, achieving real-time performance and outperforming state-of-the-art non-semantic methods by a large margin.
In this paper we introduce a novel method for general semantic segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes visually and semantically coherent image segments. We use binary encoding of CNN features to overcome the difficulty of the clustering on the high-dimensional CNN feature space. These binary codes are very robust against noise and non-semantic changes in the image. These binary encoding can be embedded into the CNN as an extra layer at the end of the network. This results in real-time segmentation. To the best of our knowledge our method is the first attempt on general semantic image segmentation using CNN. All the previous papers were limited to few number of category of the images (e.g. PASCAL VOC). Experiments show that our segmentation algorithm outperform the state-of-the-art non-semantic segmentation methods by large margin.