Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks

TL;DR

This paper introduces a novel GAN-based approach with a ranking mechanism for weakly supervised object discovery, capable of synthesizing objects, localizing categories, and enhancing detection pipelines, demonstrated on MS-COCO and PASCAL VOC datasets.

Contribution

It presents a new training method and deep similarity metric within GANs for multi-object discovery and weakly supervised detection, advancing existing methods.

Findings

Effective object synthesis in cluttered scenes

Improved weakly supervised object detection accuracy

Versatile application across datasets and scenarios

Abstract

The deep generative adversarial networks (GAN) recently have been shown to be promising for different computer vision applications, like image edit- ing, synthesizing high resolution images, generating videos, etc. These networks and the corresponding learning scheme can handle various visual space map- pings. We approach GANs with a novel training method and learning objective, to discover multiple object instances for three cases: 1) synthesizing a picture of a specific object within a cluttered scene; 2) localizing different categories in images for weakly supervised object detection; and 3) improving object discov- ery in object detection pipelines. A crucial advantage of our method is that it learns a new deep similarity metric, to distinguish multiple objects in one im- age. We demonstrate that the network can act as an encoder-decoder generating parts of an image which contain an object, or as a modified deep CNN to rep- resent images for object detection in supervised and weakly supervised scheme. Our ranking GAN offers a novel way to search through images for object specific patterns. We have conducted experiments for different scenarios and demonstrate the method performance for object synthesizing and weakly supervised object detection and classification using the MS-COCO and PASCAL VOC datasets.