Learning Effective Visual Relationship Detector on 1 GPU

12/12/2019
by   Yichao Lu, et al.
0

We present our winning solution to the Open Images 2019 Visual Relationship challenge. This is the largest challenge of its kind to date with nearly 9 million training images. Challenge task consists of detecting objects and identifying relationships between them in complex scenes. Our solution has three stages, first object detection model is fine-tuned for the challenge classes using a novel weight transfer approach. Then, spatio-semantic and visual relationship models are trained on candidate object pairs. Finally, features and model predictions are combined to generate the final relationship prediction. Throughout the challenge we focused on minimizing the hardware requirements of our architecture. Specifically, our weight transfer approach enables much faster optimization, allowing the entire architecture to be trained on a single GPU in under two days. In addition to efficient optimization, our approach also achieves superior accuracy winning first place out of over 200 teams, and outperforming the second place team by over 5% on the held-out private leaderboard.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 4

page 7

09/26/2018

A Problem Reduction Approach for Visual Relationships Detection

Identifying different objects (man and cup) is an important problem on i...
07/17/2020

2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge

In this report, we descibe our approach to the ECCV 2020 VIPriors Object...
11/01/2018

Introduction to the 1st Place Winning Model of OpenImages Relationship Detection Challenge

This article describes the model we built that achieved 1st place in the...
09/01/2018

Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions

Structured scene descriptions of images are useful for the automatic pro...
08/26/2021

Few-shot Visual Relationship Co-localization

In this paper, given a small bag of images, each containing a common but...
08/01/2018

Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features

Due to the fact that it is prohibitively expensive to completely annotat...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.