CVAICLLGSep 10, 2020

Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations

arXiv:2009.04965v38 citationsHas Code
Originality Incremental advance
AI Analysis

It addresses visual relationship detection for computer vision applications, representing an incremental improvement with novel modules and knowledge transfer.

The paper tackles visual relationship detection by proposing RVL-BERT, which incorporates visual-linguistic commonsense knowledge and novel modules like mask attention, achieving competitive results on two challenging datasets.

Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years. Inspired by human reasoning mechanisms, it is believed that external visual commonsense knowledge is beneficial for reasoning visual relationships of objects in images, which is however rarely considered in existing methods. In this paper, we propose a novel approach named Relational Visual-Linguistic Bidirectional Encoder Representations from Transformers (RVL-BERT), which performs relational reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training with multimodal representations. RVL-BERT also uses an effective spatial module and a novel mask attention module to explicitly capture spatial information among the objects. Moreover, our model decouples object detection from visual relationship recognition by taking in object names directly, enabling it to be used on top of any object detection system. We show through quantitative and qualitative experiments that, with the transferred knowledge and novel modules, RVL-BERT achieves competitive results on two challenging visual relationship detection datasets. The source code is available at https://github.com/coldmanck/RVL-BERT.

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