autofocus
autofocus copied to clipboard
uptake
Deep learning computer vision for classifying wildlife in camera trap images
@gsganden You should consider using github "Milestones" to organize all the open issues on this project. It's been really helpful [on pkgnet](https://github.com/UptakeOpenSource/pkgnet/milestones).
A la https://www.coursera.org/learn/convolutional-neural-networks/lecture/HuUtN/triplet-loss applied to animal kind recognition rather than facial recognition. Could improve ability to generalize to a new location.
See https://arxiv.org/abs/1712.00321. Has been used to promote algorithmic fairness by obscuring sensitive demographic information, but it seems applicable as well to obscuring cues that won't generalize, such as information about...
E.g. cluster empty images, and for each new image identify the closest cluster and apply standard background detection techniques. Could use as a preprocessing step for a classifier or to...
We are generally using models pretrained on ImageNet. We could use models trained on https://github.com/drivendataorg/zamba (another camera traps project) either instead of those ImageNet-trained models or as an intermediate step...
Try converting convolutional kernels of pretrained network to grayscale and applying to night images
Camera trap images taken at night use infrared light to create a grayscale image. CNNs pretrained on ImageNet may not handle these images well. One possible approach is to convert...
See how well it works as a classifier on its own, as an input to a deep learning algo, and in an ensemble with a deep learning algo
See https://petewarden.com/2018/05/28/why-you-need-to-improve-your-training-data-and-how-to-do-it/
The fastai deep learning course has some material on this topic in lesson 7 of the part 1 and in part 2. There are techniques that work better than simply...