Diversity in Object Proposals

TL;DR

This paper improves object proposal algorithms by analyzing their failure modes and combining diverse methods like Selective Search, Edge Boxes, and edge grouping to generate more accurate candidate regions for generic objects.

Contribution

The paper introduces a novel combination of segmentation and edge-based proposal methods to enhance feature diversity and reduce error modes in object proposals.

Findings

Combined strategies outperform individual methods in proposal quality.

Edge grouping helps handle objects without clear boundaries.

Diversity in features leads to higher quality object proposals.

Abstract

Current top performing object recognition systems build on object proposals as a preprocessing step. Object proposal algorithms are designed to generate candidate regions for generic objects, yet current approaches are limited in capturing the vast variety of object characteristics. In this paper we analyze the error modes of the state-of-the-art Selective Search object proposal algorithm and suggest extensions to broaden its feature diversity in order to mitigate its error modes. We devise an edge grouping algorithm for handling objects without clear boundaries. To further enhance diversity, we incorporate the Edge Boxes proposal algorithm, which is based on fundamentally different principles than Selective Search. The combination of segmentations and edges provides rich image information and feature diversity which is essential for obtaining high quality object proposals for generic objects. For a preset amount of object proposals we achieve considerably better results by using our combination of different strategies than using any single strategy alone.