MLCVLGFeb 15, 2018

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

arXiv:1802.05451v4138 citations
Originality Highly original
AI Analysis

This addresses the challenge of machine understanding of complex images with inter-related objects, offering a novel architectural design for scene graph labeling.

The paper tackled the problem of mapping images to scene graphs by proposing a design principle based on permutation invariance for structured prediction models, and it achieved new state-of-the-art results on the Visual Genome benchmark, outperforming recent approaches.

Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components. Here we propose a design principle for such architectures that follows from a natural requirement of permutation invariance. We prove a necessary and sufficient characterization for architectures that follow this invariance, and discuss its implication on model design. Finally, we show that the resulting model achieves new state of the art results on the Visual Genome scene graph labeling benchmark, outperforming all recent approaches.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes