Weaving Multi-scale Context for Single Shot Detector
arXiv:1712.03149
Abstract
Aggregating context information from multiple scales has been proved to be effective for improving accuracy of Single Shot Detectors (SSDs) on object detection. However, existing multi-scale context fusion techniques are computationally expensive, which unfavorably diminishes the advantageous speed of SSD. In this work, we propose a novel network topology, called WeaveNet, that can efficiently fuse multi-scale information and boost the detection accuracy with negligible extra cost. The proposed WeaveNet iteratively weaves context information from adjacent scales together to enable more sophisticated context reasoning while maintaining fast speed. Built by stacking light-weight blocks, WeaveNet is easy to train without requiring batch normalization and can be further accelerated by our proposed architecture simplification. Experimental results on PASCAL VOC 2007, PASCAL VOC 2012 benchmarks show signification performance boost brought by WeaveNet. For 320x320 input of batch size = 8, WeaveNet reaches 79.5% mAP on PASCAL VOC 2007 test in 101 fps with only 4 fps extra cost, and further improves to 79.7% mAP with more iterations.
References in corpus (12)
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- DSSD : Deconvolutional Single Shot Detector
- Focal Loss for Dense Object Detection
- ParseNet: Looking Wider to See Better
- Feature Pyramid Networks for Object Detection
- YOLO9000: Better, Faster, Stronger
- HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Accurate Single Stage Detector Using Recurrent Rolling Convolution
- Context-Aware Single-Shot Detector