Zoom Out-and-In Network with Recursive Training for Object Proposal

Abstract

In this paper, we propose a zoom-out-and-in network for generating object proposals. We utilize different resolutions of feature maps in the network to detect object instances of various sizes. Specifically, we divide the anchor candidates into three clusters based on the scale size and place them on feature maps of distinct strides to detect small, medium and large objects, respectively. Deeper feature maps contain region-level semantics which can help shallow counterparts to identify small objects. Therefore we design a zoom-in sub-network to increase the resolution of high level features via a deconvolution operation. The high-level features with high resolution are then combined and merged with low-level features to detect objects. Furthermore, we devise a recursive training pipeline to consecutively regress region proposals at the training stage in order to match the iterative regression at the testing stage. We demonstrate the effectiveness of the proposed method on ILSVRC DET and MS COCO datasets, where our algorithm performs better than the state-of-the-arts in various evaluation metrics. It also increases average precision by around 2% in the detection system.

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• What makes for effective detection proposals?
• Learning Deconvolution Network for Semantic Segmentation
• Stacked Hourglass Networks for Human Pose Estimation
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• Multi-Bias Non-linear Activation in Deep Neural Networks
• DeepBox: Learning Objectness with Convolutional Networks

Cited by in corpus (6)

• Object Detection in 20 Years: A Survey
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Learning Feature Pyramids for Human Pose Estimation
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
• Recent Advances in Deep Learning for Object Detection
• Recurrent Scale Approximation for Object Detection in CNN