# Deep Grouping Model for Unified Perceptual Parsing

arXiv: https://arxiv.org/abs/2003.11647 · HTML: https://mlsanity.com/paper/2003.11647/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Deep Hierarchical Semantic Segmentation](https://mlsanity.com/paper/2203.14335/) (2022)
- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention](https://mlsanity.com/paper/2304.03282/) (2023)
- [Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar'e Ball](https://mlsanity.com/paper/2404.03778/) (2024)
- [Dictionary-based Framework for Interpretable and Consistent Object Parsing](https://mlsanity.com/paper/2502.19540/) (2025)
- [OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification](https://mlsanity.com/paper/2608.30003/) (2026)

## Abstract (arXiv)

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.