• Computer Science
  • Published 2018

Biometric Fish Classification of Nordic Species Using Convolutional Neural Network with Squeeze-and-Excitation

@inproceedings{Trinh2018BiometricFC,
  title={Biometric Fish Classification of Nordic Species Using Convolutional Neural Network with Squeeze-and-Excitation},
  author={Christian M. D. Trinh and Erlend Olsvik},
  year={2018}
}
Squeeze-and-Excitation (SE) is a technique within convolutional neural networks (CNN) that can be applied to existing CNNs by applying fullyconnected layers between convolutional layers and merging the outputs. SE was the winning architecture of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2017. In this thesis, we propose a CNN using the SE architecture for classifying images of fish. Previous work in the field relies on applying filters to the images to separate the fish… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Deep Residual Learning for Image Recognition

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Fish recognition ground-truth data

  • Phoenix X. Huang, Bastiaan B. Boom, Robert B. Fisher
  • GROUNDTRUTH/RECOG/,
  • 2013
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

DeepFish: Accurate underwater live fish recognition with a deep architecture

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Adam: A Method for Stochastic Optimization

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet: A large-scale hierarchical image database

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL