Object Localization under Single Coarse Point Supervision

TL;DR

This paper introduces a novel object localization method that uses coarse point supervision, employing multiple instance learning to improve accuracy despite semantic variance in annotations.

Contribution

It proposes the first coarse point refinement approach with multiple instance learning to handle semantic variance in weak supervision for object localization.

Findings

Effective on COCO, DOTA, and SeaPerson datasets.

Outperforms existing methods with coarse supervision.

Code and dataset will be publicly available.

Abstract

Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance for the inconsistency of annotated points. Existing POL methods heavily reply on accurate key-point annotations which are difficult to define. In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points. To this end, we propose a coarse point refinement (CPR) approach, which to our best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm. CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL). In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision. Experimental results on COCO, DOTA and our proposed SeaPerson dataset validate the effectiveness of the CPR approach. The dataset and code will be available at https://github.com/ucas-vg/PointTinyBenchmark/.