no code implementations • 30 Dec 2022 • Jaya Krishna Mandivarapu, Blake Camp, Rolando Estrada
In this paper, we unify these two families of approaches from the angle of active learning using self-supervised learning mainfold and propose Deep Active Learning using BarlowTwins(DALBT), an active learning method for all the datasets using combination of classifier trained along with self-supervised loss framework of Barlow Twins to a setting where the model can encode the invariance of artificially created distortions, e. g. rotation, solarization, cropping etc.
no code implementations • 13 Nov 2020 • Blake Camp, Jaya Krishna Mandivarapu, Rolando Estrada
We demonstrate that it is possible to meta-learn a single parameter vector, which we dub a neuronal phenotype, shared by all DANs in the network, which facilitates a meta-objective during deployment.
1 code implementation • 4 Jul 2020 • Jaya Krishna Mandivarapu, Blake Camp, Rolando Estrada
The goal of active learning is to infer the informativeness of unlabeled samples so as to minimize the number of requests to the oracle.
1 code implementation • 25 May 2018 • Blake Camp, Jaya Krishna Mandivarapu, Rolando Estrada
We demonstrate that these low-dimensional vectors can then be used to generate high-fidelity recollections of the original weights.