Cost-Effective Active Learning for Deep Image Classification Cost-Effective Active Learning for Deep Image Classification
Paper summary _Objective:_ Specifically adapt Active Learning to Image Classification with deep learning _Dataset:_ [CARC]( and [Caltech-256]( ## Inner-workings: They labels from two sources: * The most informative/uncertain samples are manually labeled using Least confidence, margin sampling and entropy, see [Active Learning Literature Survey]( * The other kind is the samples with high prediction confidence that are automatically labelled. They represent the majority of samples. ## Architecture: [![screen shot 2017-06-29 at 3 57 43 pm](]( They proceed with the following steps: 1. Initialization: they manually annotate a given number of images for each class in order to pre-trained the network. 2. Complementary sample selection: they fix the network, identity the most uncertain label for manual annotation and automatically annotate the most certain one if their entropy is higher than a given threshold. 3. CNN fine-tuning: they train the network using the whole pool of already labeled data and pseudo-labeled. Then they put all the automatically labeled images back into the unlabelled pool. 4. Threshold updating: as the network gets more and more confident the threshold for auto-labelling is linearly reducing. The idea is that the network gets a more reliable representation and its trustability increases. ## Results: Roughly divide by 2 the number of annotation needed. ⚠️ I don't feel like this paper can be trusted 100% ⚠️
Cost-Effective Active Learning for Deep Image Classification
Wang, Keze and Zhang, Dongyu and Li, Ya and Zhang, Ruimao and Lin, Liang
IEEE Trans. Circuits Syst. Video Techn. - 2017 via Local Bibsonomy
Keywords: dblp

Summary by Léo Paillier 2 weeks ago
Your comment: allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and