Single-Shot Refinement Neural Network for Object Detection

Abstract

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at https://github.com/sfzhang15/RefineDet

14 pages, 7 figures, 7 tables

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• DSSD : Deconvolutional Single Shot Detector
• Focal Loss for Dense Object Detection
• ParseNet: Looking Wider to See Better
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Feature Pyramid Networks for Object Detection
• YOLO9000: Better, Faster, Stronger
• Deformable Convolutional Networks
• Aggregated Residual Transformations for Deep Neural Networks
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Speed/accuracy trade-offs for modern convolutional object detectors
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• DSOD: Learning Deeply Supervised Object Detectors from Scratch
• FaceBoxes: A CPU Real-time Face Detector with High Accuracy
• Scalable Object Detection using Deep Neural Networks

Cited by in corpus (9)

• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• A Review of Object Detection Models based on Convolutional Neural Network
• CornerNet: Detecting Objects as Paired Keypoints
• Region Proposal by Guided Anchoring
• PyramidBox: A Context-assisted Single Shot Face Detector
• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• Deep Feature Pyramid Reconfiguration for Object Detection