Point Linking Network for Object Detection

TL;DR

This paper introduces Point Linking Network (PLN), a novel object detection approach that regresses key points and links to form bounding boxes, improving robustness to occlusion and scale variation, achieving state-of-the-art results.

Contribution

The paper presents a new bounding box representation using points and links, implemented with deep ConvNets, enhancing object detection performance and robustness.

Findings

Achieves state-of-the-art results on PASCAL VOC and COCO benchmarks.

Robust to occlusion and scale variations.

Effective point and link regression approach.

Abstract

Object detection is a core problem in computer vision. With the development of deep ConvNets, the performance of object detectors has been dramatically improved. The deep ConvNets based object detectors mainly focus on regressing the coordinates of bounding box, e.g., Faster-R-CNN, YOLO and SSD. Different from these methods that considering bounding box as a whole, we propose a novel object bounding box representation using points and links and implemented using deep ConvNets, termed as Point Linking Network (PLN). Specifically, we regress the corner/center points of bounding-box and their links using a fully convolutional network; then we map the corner points and their links back to multiple bounding boxes; finally an object detection result is obtained by fusing the multiple bounding boxes. PLN is naturally robust to object occlusion and flexible to object scale variation and aspect ratio variation. In the experiments, PLN with the Inception-v2 model achieves state-of-the-art single-model and single-scale results on the PASCAL VOC 2007, the PASCAL VOC 2012 and the COCO detection benchmarks without bells and whistles. The source code will be released.