# DAG-Recurrent Neural Networks For Scene Labeling

arXiv: https://arxiv.org/abs/1509.00552 · HTML: https://mlsanity.com/paper/1509.00552/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2015.

## Built on by (most cited first, 10 of 10)

- [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://mlsanity.com/paper/2105.12907/) (2021)
- [Directed Acyclic Graph Neural Networks](https://mlsanity.com/paper/2101.07965/) (2021)
- [Transformers over Directed Acyclic Graphs](https://mlsanity.com/paper/2210.13148/) (2022)
- [Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph](https://mlsanity.com/paper/2409.11504/) (2024)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Addressing Variable Dependency in GNN-based SAT Solving](https://mlsanity.com/paper/2304.08738/) (2023)
- [Towards Invertible Semantic-Preserving Embeddings of Logical Formulae](https://mlsanity.com/paper/2305.03143/) (2023)
- [Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs](https://mlsanity.com/paper/2408.07394/) (2024)
- [ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time](https://mlsanity.com/paper/2305.10611/) (2023)
- [Progressively Dual Prior Guided Few-shot Semantic Segmentation](https://mlsanity.com/paper/2211.15467/) (2022)

## Abstract (arXiv)

In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded. In this paper, we introduce recurrent neural networks (RNNs) to address this issue. Specifically, directed acyclic graph RNNs (DAG-RNNs) are proposed to process DAG-structured images, which enables the network to model long-range semantic dependencies among image units. Our DAG-RNNs are capable of tremendously enhancing the discriminative power of local representations, which significantly benefits the local classification. Meanwhile, we propose a novel class weighting function that attends to rare classes, which phenomenally boosts the recognition accuracy for non-frequent classes. Integrating with convolution and deconvolution layers, our DAG-RNNs achieve new state-of-the-art results on the challenging SiftFlow, CamVid and Barcelona benchmarks.