Multi-peak Graph-based Multi-instance Learning for Weakly Supervised Object Detection

Ruyi Ji

doi:10.1145/3432861

Multi-peak Graph-based Multi-instance Learning for Weakly Supervised Object Detection

2021-06-14

9

PRE

AI

DOI：10.1145/3432861

Original request for help

Save

Abstract

En 中文

Weakly supervised object detection (WSOD), aiming to detect objects with only image-level annotations, has become one of the research hotspots over the past few years. Recently, much effort has been devoted to WSOD for the simple yet effective architecture and remarkable improvements have been achieved. Existing approaches using multiple-instance learning usually pay more attention to the proposals individually, ignoring relation information between proposals. Besides, to obtain pseudo-ground-truth boxes for WSOD, MIL-based methods tend to select the region with the highest confidence score and regard those with small overlap as background category, which leads to mislabeled instances. As a result, these methods suffer from mislabeling instances and lacking relations between proposals, degrading the performance of WSOD. To tackle these issues, this article introduces a multi-peak graph-based model for WSOD. Specifically, we use the instance graph to model the relations between proposals, which reinforces multiple-instance learning process. In addition, a multi-peak discovery strategy is designed to avert mislabeling instances. The proposed model is trained by stochastic gradients decent optimizer using back-propagation in an end-to-end manner. Extensive quantitative and qualitative evaluations on two publicly challenging benchmarks, PASCAL VOC 2007 and PASCAL VOC 2012, demonstrate the superiority and effectiveness of the proposed approach.

Keywords:

Weakly supervised object detection

multi-instance learning

context information

graph neural network

Multi-peak Graph-based Multi-instance Learning for Weakly Supervised Object Detection

Abstract

AI Summary

Journal

Organization