Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

Citations Over TimeTop 1% of 2016 papers

Abstract

In this paper, we investigate two new strategies to detect objects accurately and efficiently using deep convolutional neural network: 1) scale-dependent pooling and 2) layerwise cascaded rejection classifiers. The scale-dependent pooling (SDP) improves detection accuracy by exploiting appropriate convolutional features depending on the scale of candidate object proposals. The cascaded rejection classifiers (CRC) effectively utilize convolutional features and eliminate negative object proposals in a cascaded manner, which greatly speeds up the detection while maintaining high accuracy. In combination of the two, our method achieves significantly better accuracy compared to other state-of-the-arts in three challenging datasets, PASCAL object detection challenge, KITTI object detection benchmark and newly collected Inner-city dataset, while being more efficient.

Related Papers

• → Multiactivation Pooling Method in Convolutional Neural Networks for Image Recognition(2018)27 cited
• → Object detection using improved YOLOv3-tiny based on pyramid pooling(2021)1 cited
• → Application of Convolutional Neural Network for Image Classification on\n Pascal VOC Challenge 2012 dataset(2016)18 cited
• → Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset(2016)15 cited
• → Improved Regional Proposal Generation and Proposal Selection Method for Weakly Supervision Object detection(2023)