Object Detection in Junk Image Based on SSD Model

Zhihao Guan

doi:10.54097/fcis.v2i3.5414

Authors

Zhihao Guan

DOI:

https://doi.org/10.54097/fcis.v2i3.5414

Keywords:

Target detection, SSD, Single-shot multi-frame detection, Taco dataset, Garbage detection

Abstract

This paper first introduces the background and significance of the direction in target detection, and introduces other target detection methods besides SSD. Secondly, this paper also introduces the principle and implementation process of SSD. It describes in detail the important steps to implement SSD and attaches relevant codes. Finally, the achieved results are compared with different methods, different data sets VOC 07 and networks using different methods, and conclusions are drawn.

Downloads

Download data is not yet available.

References

Hochreiter S,Schmidhuber J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.

Chung J,Gulcehre C,Cho K H,et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv preprint arXiv:1412. 3555,2014.

Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning [J]. Nature, 2015, 518 (7540):529-533.

Weston J,Chopra S,Bordes A. Memory networks[J]. arXiv preprint arXiv:1410. 3916,2014.

[Sukhbaatar S,Weston J,Fergus R. End-to-end memory networks [C] / / Advances in Neural Information Processing Systems (NIPS),2015:2440-2448

Pritzel A,Uria B,Srinivasan S,et al. Neural episodic control[C] / / International Conference on Machine Learning(ICML),2015.

Graves A,Wayne G,Danihelka I. Neural turing machines[J]. arXiv preprint arXiv:1410. 5401,2014.

Graves A,Wayne G,Reynolds M,et al. Hybrid computing using a neural network with dynamic external memory[ J]. Nature,2016, 538(7626):471-476.

Sukhbaatar S, Szlam A, Weston J,Fergus R. End-to-end memory networks//Proceedings of the Annual Conferenceon Neural Information Processing Systems. Montreal, Canada, 2015:2440-2448

Vaswani A,Shazeer N,Parmar N,etal .Attention is all you need//Proceedings of the Annual Conferenceon Neural Information Processing Systems . LongBeach, USA, 2017: 5998-600

Lin L J. Self-improving reactive agents based on reinforcement learning,planning and teaching[ J]. Machine Learning,1992,8(3- 4):293-321.

Schaul T,Quan J,Antonoglou I,et al. Prioritized experience replay [C] / / International Conference on Learning Representations (ICLR),2016.