Generating Discriminative Object Proposals via Submodular Ranking

TL;DR

This paper introduces a multi-scale, submodular ranking approach for generating diverse and discriminative object proposals based on hierarchical image segmentation, improving accuracy and efficiency in object detection tasks.

Contribution

It proposes a novel submodular optimization framework that combines coverage, diversity, and multi-scale discrimination for object proposal generation.

Findings

Outperforms state-of-the-art methods on PASCAL VOC2012 and Berkeley datasets.

Achieves higher accuracy in object detection and segmentation tasks.

Demonstrates efficiency in proposal generation process.

Abstract

A multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation. We first identify the representative and diverse exemplar clusters within each scale by using a diversity ranking algorithm. Object proposals are obtained by selecting a subset from the multi-scale segment pool via maximizing a submodular objective function, which consists of a weighted coverage term, a single-scale diversity term and a multi-scale reward term. The weighted coverage term forces the selected set of object proposals to be representative and compact; the single-scale diversity term encourages choosing segments from different exemplar clusters so that they will cover as many object patterns as possible; the multi-scale reward term encourages the selected proposals to be discriminative and selected from multiple layers generated by the hierarchical image segmentation. The experimental results on the Berkeley Segmentation Dataset and PASCAL VOC2012 segmentation dataset demonstrate the accuracy and efficiency of our object proposal model. Additionally, we validate our object proposals in simultaneous segmentation and detection and outperform the state-of-art performance.