Small Object Detection Based on Modified FSSD and Model Compression
Authors:
- 22 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 88-92
Abstract
Small objects have relatively low resolution, the unobvious visual features which are difficult to be extracted, so the existing object detection methods cannot effectively detect small objects, and the detection speed and stability are poor. Thus, this paper proposes a small object detection algorithm based on FSSD, meanwhile, in order to reduce the computational cost and storage space, pruning is carried out to achieve model compression. Firstly, the semantic information contained in the features of different layers can be used to detect different scale objects, and the feature fusion method is improved to obtain more information beneficial to small objects; secondly, batch normalization layer is introduced to accelerate the training of neural network and make the model sparse; finally, the model is pruned by scaling factor to get the corresponding compressed model. The experimental results show that the average accuracy (mAP) of the algorithm can reach 80.4% on PASCAL VOC and the speed is 59.5 FPS on GTX1080ti. After pruning, the compressed model can reach 79.9% mAP, and 79.5 FPS in detection speed. On MS COCO, the best detection accuracy (APs) is 12.1%, and the overall detection accuracy is 49.8% AP when IoU is 0.5. The algorithm can not only improve the detection accuracy of small objects, but also greatly improves the detection speed, which reaches a balance between speed and accuracy.Keywords
All Related Versions
Funding Information
- Innovation Fund
This publication has 12 references indexed in Scilit:
- Receptive Field Block Net for Accurate and Fast Object Detection2018
- Mask R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- A discriminatively trained, multiscale, deformable part model2008
- Histograms of Oriented Gradients for Human Detection2005
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004