PhraseCut: Language-based Image Segmentation in the Wild
This addresses the challenge of language-based image segmentation for computer vision applications, but it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of segmenting image regions based on natural language phrases by creating a large-scale dataset of 77,262 images and 345,486 phrase-region pairs, and their modular approach combining category, attribute, and relationship cues outperformed existing methods.
We consider the problem of segmenting image regions given a natural language phrase, and study it on a novel dataset of 77,262 images and 345,486 phrase-region pairs. Our dataset is collected on top of the Visual Genome dataset and uses the existing annotations to generate a challenging set of referring phrases for which the corresponding regions are manually annotated. Phrases in our dataset correspond to multiple regions and describe a large number of object and stuff categories as well as their attributes such as color, shape, parts, and relationships with other entities in the image. Our experiments show that the scale and diversity of concepts in our dataset poses significant challenges to the existing state-of-the-art. We systematically handle the long-tail nature of these concepts and present a modular approach to combine category, attribute, and relationship cues that outperforms existing approaches.