Active Learning for Convolutional Neural Networks: A Core-Set Approach — mentioned by MalteEbner

Mon, 09 Aug 2021 15:49:51 GMT

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…

Paper and discussion history. A mention is not an endorsement.

Active Learning for Convolutional Neural Networks: A Core-Set Approach — HN submission

Tue, 08 Aug 2017 14:47:52 GMT

A Geometric Approach to Active Learning for Convolutional Neural Networks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Active Learning for Convolutional Neural Networks: A Core-Set Approach · HackerPapers discussions

Active Learning for Convolutional Neural Networks: A Core-Set Approach — mentioned by MalteEbner

Active Learning for Convolutional Neural Networks: A Core-Set Approach — HN submission