CNN-aware Binary Map for General Semantic Segmentation

TL;DR

This paper presents a real-time, CNN-based semantic segmentation method using binary encoding of CNN features, achieving superior results on diverse image categories by leveraging semantic coherence and robustness against noise.

Contribution

Introduces a novel binary encoding approach for CNN features to enable real-time, general semantic segmentation across diverse categories, outperforming existing non-semantic methods.

Findings

Outperforms state-of-the-art non-semantic segmentation methods

Achieves real-time segmentation with binary CNN feature encoding

Effective on diverse, multi-category image datasets

Abstract

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.