Unsupervised segmentation via semantic-apparent feature fusion

TL;DR

This paper introduces an unsupervised foreground segmentation method that fuses semantic and apparent features, achieving superior performance by adaptively weighting features and learning common foreground characteristics across images.

Contribution

It proposes a novel semantic-apparent feature fusion approach with adaptive parameter learning for unsupervised segmentation, outperforming existing methods.

Findings

Significantly exceeds baseline performance on PASCAL VOC 2012.

Effectively combines semantic and apparent features for stable segmentation.

Adaptive feature weighting improves segmentation accuracy.

Abstract

Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation performance based on fixed rules or single type of feature. In order to solve this problem, the research proposes an unsupervised foreground segmentation method based on semantic-apparent feature fusion (SAFF). Here, we found that key regions of foreground object can be accurately responded via semantic features, while apparent features (represented by saliency and edge) provide richer detailed expression. To combine the advantages of the two type of features, an encoding method for unary region features and binary context features is established, which realizes a comprehensive description of the two types of expressions. Then, a method for adaptive parameter learning is put forward to calculate the most suitable feature weights and generate foreground confidence score map. Furthermore, segmentation network is used to learn foreground common features from different instances. By fusing semantic and apparent features, as well as cascading the modules of intra-image adaptive feature weight learning and inter-image common feature learning, the research achieves performance that significantly exceeds baselines on the PASCAL VOC 2012 dataset.