NODIS: Neural Ordinary Differential Scene Understanding

TL;DR

This paper introduces NODIS, a novel neural ODE-based architecture for scene graph inference in images, achieving state-of-the-art results in semantic scene understanding tasks by end-to-end learning.

Contribution

It reformulates relation inference as a neural ODE, enabling end-to-end training and improved performance over previous methods.

Findings

Achieves state-of-the-art results on Visual Genome benchmarks.

Effectively models relations using neural ODEs.

Outperforms previous approaches in scene graph tasks.

Abstract

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.