---
title: "Learning Unsupervised Visual Grounding Through Semantic Self-Supervision"
authors:
  - "Syed Ashar Javed"
  - "Shreyas Saxena"
  - "Vineet Gandhi"
doi: "10.24963/ijcai.2019/112"
url: "https://ijcai.org/proceedings/2019/112"
pdf: "https://ijcai.org/proceedings/2019/0112.pdf"
venue: "Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"
year: 2019
pages: "796-802"
track: "Main track"
keywords:
  - "Computer Vision: Language and Vision"
  - "Machine Learning: Unsupervised Learning"
  - "Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"
---

# Learning Unsupervised Visual Grounding Through Semantic Self-Supervision

Syed Ashar Javed, Shreyas Saxena, Vineet Gandhi

*Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence*, pages 796-802. DOI: [10.24963/ijcai.2019/112](https://doi.org/10.24963/ijcai.2019/112)

## Abstract

Localizing natural language phrases in images is a challenging problem that requires joint understanding of both the textual and visual modalities. In the unsupervised setting, lack of supervisory signals exacerbate this difficulty. In this paper, we propose a novel framework for unsupervised visual grounding which uses concept learning as a proxy task to obtain self-supervision. The intuition behind this idea is to encourage the model to localize to regions which can explain some semantic property in the data, in our case, the property being the presence of a concept in a set of images. We present thorough quantitative and qualitative experiments to demonstrate the efficacy of our approach and show a 5.6% improvement over the current state of the art on Visual Genome dataset, a 5.8% improvement on the ReferItGame dataset and comparable to state-of-art performance on the Flickr30k dataset.