Background lit rev on models

# Background lit rev on models ###### tags: `references`, `models` ## Papers - (Schroeder et al. 2020) MorphoCluster: Efficient Annotation of Plankton images by Clustering https://arxiv.org/abs/2005.01595 Model: **ResNet18** Github: https://github.com/morphocluster - (Ellen et al. 2019) Improving plankton image classification using context metadata https://aslopubs.onlinelibrary.wiley.com/doi/full/10.1002/lom3.10324 Model: **VGG-16** - (Lumini et al. 2019) Deep Learning for Plankton and Coral Classification https://arxiv.org/ftp/arxiv/papers/1908/1908.05489.pdf (pdf) https://arxiv.org/abs/1908.05489 (online) Tested: **AlexNet, GoogleNet, InceptionV3, VGGNet, ResNet50, ResNet101, DenseNet, MobileNetV2, NasNet** Key messages: "The experimental results show that the best stand-alone model for most of the target datasets is **DenseNet**. [...] We show how to create an **ensemble** which improves the performance of the best single model." - (Li et al. 2021) Plankton Detection with Adversarial Learning and a Densely Connected Deep Learning Model for Class Imbalanced Distribution https://www.mdpi.com/2077-1312/9/6/636/pdf (pdf) https://doi.org/10.3390/jmse9060636 (online) Key message: Nice review of models that have been tested already. - (Cheng et al. 2019) Enhanced convolutional neural network for plankton identification and enumeration [pdf](https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0219570&type=printable ) [online](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0219570) Key messages: "Among the selected CNN models, the ResNet50 performed the best." Tested: **AlexNet, VGG16, VGG19, GoogLeNet, and ResNet** - (Bello et al., 2021) Revisiting ResNets: Improved Training and Scaling Strategies Model: **ResNet-RS-420** https://arxiv.org/pdf/2103.07579 (pdf) https://arxiv.org/abs/2103.07579 (online) Github: https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs - (Chen et al. 2019) Dynamic Convolution: Attention over Convolution Kernels Model: **ResNet18** https://arxiv.org/pdf/1912.03458v2.pdf (pdf) https://arxiv.org/abs/1912.03458v2 (online) # Size images - https://blog.roboflow.com/you-might-be-resizing-your-images-incorrectly/ - https://benanne.github.io/2015/03/17/plankton.html # Monochrome ## Other references we stumbled across (Zheng et al. 2017) Automatic plankton image classification combining multiple view features via multiple kernel learning https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-017-1954-8 StyleGAN https://www.mdpi.com/2077-1312/9/6/636/pdf