Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2020

Abstract

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the con-textual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). We extensively apply VC R-CNN features in prevailing models of two popular tasks: Image Captioning and VQA, and observe consistent performance boosts across all the methods, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN. For better clarity, you can also refer to the full version of this paper in [11].

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Virtual Conference, June 14-19

First Page

1

Last Page

4

Identifier

10.1109/CVPRW50498.2020.00197

Publisher

IEEE

City or Country

Virtual Conference

Share

COinS