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

by   Ji Zhang, et al.

This article describes the model we built that achieved 1st place in the OpenImage Visual Relationship Detection Challenge on Kaggle. Three key factors contribute the most to our success: 1) language bias is a powerful baseline for this task. We build the empirical distribution P(predicate|subject,object) in the training set and directly use that in testing. This baseline achieved the 2nd place when submitted; 2) spatial features are as important as visual features, especially for spatial relationships such as "under" and "inside of"; 3) It is a very effective way to fuse different features by first building separate modules for each of them, then adding their output logits before the final softmax layer. We show in ablation study that each factor can improve the performance to a non-trivial extent, and the model reaches optimal when all of them are combined.



There are no comments yet.


page 2

page 3


An Interpretable Model for Scene Graph Generation

We propose an efficient and interpretable scene graph generator. We cons...

Learning Effective Visual Relationship Detector on 1 GPU

We present our winning solution to the Open Images 2019 Visual Relations...

A Problem Reduction Approach for Visual Relationships Detection

Identifying different objects (man and cup) is an important problem on i...

Visual Relationship Detection with Language prior and Softmax

Visual relationship detection is an intermediate image understanding tas...

Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration

Convolutional Neural Networks (CNNs) have recently been shown to excel a...

CPARR: Category-based Proposal Analysis for Referring Relationships

The task of referring relationships is to localize subject and object en...

Evaluating Perceptual Bias During Geometric Scaling of Scatterplots

Scatterplots are frequently scaled to fit display areas in multi-view an...
This week in AI

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