# Deep Hierarchical Parsing for Semantic Segmentation

arXiv: https://arxiv.org/abs/1503.02725 · HTML: https://mlsanity.com/paper/1503.02725/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2015.

## Built on by (most cited first, 6 of 6)

- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar'e Ball](https://mlsanity.com/paper/2404.03778/) (2024)
- [Tree semantic segmentation from aerial image time series](https://mlsanity.com/paper/2407.13102/) (2024)
- [Learning Neural Parsers with Deterministic Differentiable Imitation Learning](https://mlsanity.com/paper/1806.07822/) (2018)
- [Deep Learning Model with GA based Feature Selection and Context Integration](https://mlsanity.com/paper/2204.06189/) (2022)
- [Context-based Deep Learning Architecture with Optimal Integration Layer for Image Parsing](https://mlsanity.com/paper/2204.06214/) (2022)

## Abstract (arXiv)

This paper proposes a learning-based approach to scene parsing inspired by the deep Recursive Context Propagation Network (RCPN). RCPN is a deep feed-forward neural network that utilizes the contextual information from the entire image, through bottom-up followed by top-down context propagation via random binary parse trees. This improves the feature representation of every super-pixel in the image for better classification into semantic categories. We analyze RCPN and propose two novel contributions to further improve the model. We first analyze the learning of RCPN parameters and discover the presence of bypass error paths in the computation graph of RCPN that can hinder contextual propagation. We propose to tackle this problem by including the classification loss of the internal nodes of the random parse trees in the original RCPN loss function. Secondly, we use an MRF on the parse tree nodes to model the hierarchical dependency present in the output. Both modifications provide performance boosts over the original RCPN and the new system achieves state-of-the-art performance on Stanford Background, SIFT-Flow and Daimler urban datasets.