Multiresolution hierarchy co-clustering for semantic segmentation in sequences with small variations
This work addresses video segmentation challenges for scenarios with minimal changes, though it appears incremental as it builds on existing co-clustering and hierarchy methods.
The paper tackles the problem of semantic segmentation in video sequences with small variations by introducing a co-clustering technique that uses image hierarchies to create coherent multiresolution representations, achieving state-of-the-art results on the Video Occlusion/Object Boundary Detection Dataset.
This paper presents a co-clustering technique that, given a collection of images and their hierarchies, clusters nodes from these hierarchies to obtain a coherent multiresolution representation of the image collection. We formalize the co-clustering as a Quadratic Semi-Assignment Problem and solve it with a linear programming relaxation approach that makes effective use of information from hierarchies. Initially, we address the problem of generating an optimal, coherent partition per image and, afterwards, we extend this method to a multiresolution framework. Finally, we particularize this framework to an iterative multiresolution video segmentation algorithm in sequences with small variations. We evaluate the algorithm on the Video Occlusion/Object Boundary Detection Dataset, showing that it produces state-of-the-art results in these scenarios.