TY - CONF AB - We present a new proximal bundle method for Maximum-A-Posteriori (MAP) inference in structured energy minimization problems. The method optimizes a Lagrangean relaxation of the original energy minimization problem using a multi plane block-coordinate Frank-Wolfe method that takes advantage of the specific structure of the Lagrangean decomposition. We show empirically that our method outperforms state-of-the-art Lagrangean decomposition based algorithms on some challenging Markov Random Field, multi-label discrete tomography and graph matching problems. AU - Swoboda, Paul AU - Kolmogorov, Vladimir ID - 7468 SN - 10636919 T2 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition TI - Map inference via block-coordinate Frank-Wolfe algorithm VL - 2019-June ER - TY - JOUR AU - Morandell, Jasmin AU - Nicolas, Armel AU - Schwarz, Lena A AU - Novarino, Gaia ID - 7415 IS - Supplement 6 JF - European Neuropsychopharmacology SN - 0924-977X TI - S.16.05 Illuminating the role of the e3 ubiquitin ligase cullin3 in brain development and autism VL - 29 ER - TY - JOUR AU - Knaus, Lisa AU - Tarlungeanu, Dora-Clara AU - Novarino, Gaia ID - 7414 IS - Supplement 6 JF - European Neuropsychopharmacology SN - 0924-977X TI - S.16.03 A homozygous missense mutation in SLC7A5 leads to autism spectrum disorder and microcephaly VL - 29 ER - TY - JOUR AU - Benková, Eva AU - Dagdas, Yasin ID - 7394 IS - 12 JF - Current Opinion in Plant Biology SN - 1369-5266 TI - Editorial overview: Cell biology in the era of omics? VL - 52 ER - TY - CONF AB - Multi-exit architectures, in which a stack of processing layers is interleaved with early output layers, allow the processing of a test example to stop early and thus save computation time and/or energy. In this work, we propose a new training procedure for multi-exit architectures based on the principle of knowledge distillation. The method encourage searly exits to mimic later, more accurate exits, by matching their output probabilities. Experiments on CIFAR100 and ImageNet show that distillation-based training significantly improves the accuracy of early exits while maintaining state-of-the-art accuracy for late ones. The method is particularly beneficial when training data is limited and it allows a straightforward extension to semi-supervised learning,i.e. making use of unlabeled data at training time. Moreover, it takes only afew lines to implement and incurs almost no computational overhead at training time, and none at all at test time. AU - Bui Thi Mai, Phuong AU - Lampert, Christoph ID - 7479 SN - 15505499 T2 - IEEE International Conference on Computer Vision TI - Distillation-based training for multi-exit architectures VL - 2019-October ER -