MalteEbner

Nice to see that distillation also works well. That means I can take the huge pretrained dinov2 models and distill them to my custom model architecture. Very nice!

modAL indeed has a similar goal of choosing the best subset of data to be labeled. However it has some notable differences:

It is built on scikit-learn which is also evident from the suggested workflow. Lightly on the other hand was specifically built for deep learning applications supporting active learning for classification but also object detection and semantic segmentation.

modAL provides uncertainty-based active learning. However, it has been shown that uncertainty-based AL fails at batch-wise AL for vision datasets and CNNs, see https://arxiv.org/abs/1708.00489. Furthermore it only works with an initially trained model and thus labeled dataset. Lightly offers self-supervised learning to learn high dimensional embeddings through its open-source package https://github.com/lightly-ai/lightly. They can be used through our API to choose a diverse subset. Optionally, this sampling can be combined with uncertainty-based AL.