image-quality-assessment VS efficientnet

It's an ongoing research area, but here's a Google model that assigns images ratings based on how good they look. It's pretty good, and it's from 2019 so not even close to state of the art. Paired with Stable Diffusion, it could indeed curate itself. I might have to try that actually.

Examples of lightweight models include MobileNet, a computer vision model designed for mobile and embedded vision applications, EfficientDet, an object detection model, and EfficientNet, a CNN that uses compound scaling to enable better performance. All these are lightweight models from Google.

There was a recent paper by Facebook (2022), where they modernise a vanilla ConvNet by using the latest empirical design choices and manage to achieve state-of-the-art performance with it. This was also done before, with EffecientNet in 2019.

not true at all, plenty of sota models combines batchnorm and dropout 1. efficientnet 2. resnet rs 3. timm resnet50 (appendix)

Right - I think these days they do more of a balanced tradeoff between width and depth. One more recent CNN, Efficientnet, carefully chooses the width-to-depth ratio to have the best performance for a given compute budget.

EfficientNet a lightweight convolutional neural network architecture achieving the state-of-the-art accuracy with an order of magnitude fewer parameters and FLOPS, on both ImageNet and five other commonly used transfer learning datasets.

Additionally, if you want to custom change the number of filters in the EfficientNet I would suggest using the detailed Keras implementation of the EfficientNet in this repository.