# NODIS: Neural Ordinary Differential Scene Understanding

arXiv: https://arxiv.org/abs/2001.04735 · HTML: https://mlsanity.com/paper/2001.04735/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 12 of 12)

- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [Spatial-Temporal Transformer for Dynamic Scene Graph Generation](https://mlsanity.com/paper/2107.12309/) (2021)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021)
- [BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation](https://mlsanity.com/paper/2109.05346/) (2021)
- [Explore Contextual Information for 3D Scene Graph Generation](https://mlsanity.com/paper/2210.06240/) (2022)
- [DDS: Decoupled Dynamic Scene-Graph Generation Network](https://mlsanity.com/paper/2301.07666/) (2023)
- [SPAN: Learning Similarity between Scene Graphs and Images with Transformers](https://mlsanity.com/paper/2304.00590/) (2023)
- [Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction](https://mlsanity.com/paper/2311.04834/) (2023)
- [SGTR+: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2401.12835/) (2024)

## Abstract (arXiv)

Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image. In previous works, relations were identified by solving an assignment problem formulated as Mixed-Integer Linear Programs. In this work, we interpret that formulation as Ordinary Differential Equation (ODE). The proposed architecture performs scene graph inference by solving a neural variant of an ODE by end-to-end learning. It achieves state-of-the-art results on all three benchmark tasks: scene graph generation (SGGen), classification (SGCls) and visual relationship detection (PredCls) on Visual Genome benchmark.