To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data.
Ranked #1 on Partial Domain Adaptation on ImageNet-Caltech
By learning minimum sufficient representations from training data, the information bottleneck (IB) approach has demonstrated its effectiveness to improve generalization in different AI applications.
Real-world data is usually segmented by attributes and distributed across different parties.
We introduce the matrix-based Renyi's $\alpha$-order entropy functional to parameterize Tishby et al. information bottleneck (IB) principle with a neural network.
Measuring the dependence of data plays a central role in statistics and machine learning.