Object Localization under Single Coarse Point Supervision

by   Xuehui Yu, et al.
University of the Chinese Academy of Sciences

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/.


page 2

page 4

page 6

page 7

page 11

page 12

page 13

page 14


A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays

Accurate abnormality localization in chest X-rays (CXR) can benefit the ...

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

In this paper, we present a conceptually simple, strong, and efficient f...

Iterative Superquadric Recomposition of 3D Objects from Multiple Views

Humans are good at recomposing novel objects, i.e. they can identify com...

Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images

Developing an AI-assisted gland segmentation method from histology image...

Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection

Single-frame infrared small target (SIRST) detection aims at separating ...

Point-Query Quadtree for Crowd Counting, Localization, and More

We show that crowd counting can be viewed as a decomposable point queryi...

An extensible point-based method for data chart value detection

We present an extensible method for identifying semantic points to rever...

Please sign up or login with your details

Forgot password? Click here to reset