Deep Grouping Model for Unified Perceptual Parsing
This work addresses the problem of improving interpretability and performance in image segmentation for computer vision researchers, though it is incremental as it builds on existing grouping and CNN methods.
The paper tackles the challenge of integrating perceptual grouping processes with CNN-based image segmentation, which are inherently incompatible due to grid-shaped feature maps and irregular-shaped hierarchies. The proposed deep grouping model (DGM) achieves state-of-the-art results on the Broden+ dataset for unified perceptual parsing with small computational overhead.
The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts. Examples can be found in the classical hierarchical superpixel segmentation or image parsing works. However, the grouping process is largely overlooked in modern CNN-based image segmentation networks due to many challenges, including the inherent incompatibility between the grid-shaped CNN feature map and the irregular-shaped perceptual grouping hierarchy. Overcoming these challenges, we propose a deep grouping model (DGM) that tightly marries the two types of representations and defines a bottom-up and a top-down process for feature exchanging. When evaluating the model on the recent Broden+ dataset for the unified perceptual parsing task, it achieves state-of-the-art results while having a small computational overhead compared to other contextual-based segmentation models. Furthermore, the DGM has better interpretability compared with modern CNN methods.