%0 Journal Article %1 sinha2020diversity %A Sinha, Samarth %A Bharadhwaj, Homanga %A Goyal, Anirudh %A Larochelle, Hugo %A Garg, Animesh %A Shkurti, Florian %D 2020 %K bayesian uncertainty %T DIBS: Diversity inducing Information Bottleneck in Model Ensembles %U http://arxiv.org/abs/2003.04514 %X Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research. Bayesian approaches including Bayesian Neural Nets (BNNs) do not scale well to modern computer vision tasks, as they are difficult to train, and have poor generalization under dataset-shift. This motivates the need for effective ensembles which can generalize and give reliable uncertainty estimates. In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning the stochastic latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. We evaluate our method on benchmark datasets: MNIST, CIFAR100, TinyImageNet and MIT Places 2, and compared to the most competitive baselines show significant improvements in classification accuracy, under a shift in the data distribution and in out-of-distribution detection. Code will be released in this url https://github.com/rvl-lab-utoronto/dibs

@article{sinha2020diversity, abstract = {Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research. Bayesian approaches including Bayesian Neural Nets (BNNs) do not scale well to modern computer vision tasks, as they are difficult to train, and have poor generalization under dataset-shift. This motivates the need for effective ensembles which can generalize and give reliable uncertainty estimates. In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning the stochastic latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. We evaluate our method on benchmark datasets: MNIST, CIFAR100, TinyImageNet and MIT Places 2, and compared to the most competitive baselines show significant improvements in classification accuracy, under a shift in the data distribution and in out-of-distribution detection. Code will be released in this url https://github.com/rvl-lab-utoronto/dibs}, added-at = {2020-03-11T20:32:47.000+0100}, author = {Sinha, Samarth and Bharadhwaj, Homanga and Goyal, Anirudh and Larochelle, Hugo and Garg, Animesh and Shkurti, Florian}, biburl = {https://www.bibsonomy.org/bibtex/2ca87c0809412a8e5b22e222b172aa518/kirk86}, description = {[2003.04514] DIBS: Diversity inducing Information Bottleneck in Model Ensembles}, interhash = {0d07193cc144a79ff01ae744b0f36d86}, intrahash = {ca87c0809412a8e5b22e222b172aa518}, keywords = {bayesian uncertainty}, note = {cite arxiv:2003.04514Comment: Samarth Sinha* and Homanga Bharadhwaj* contributed equally to this work. Code will be released at https://github.com/rvl-lab-utoronto/dibs}, timestamp = {2020-03-11T20:32:47.000+0100}, title = {DIBS: Diversity inducing Information Bottleneck in Model Ensembles}, url = {http://arxiv.org/abs/2003.04514}, year = 2020 }