44 citations · 122 across the 16 of their papers we have counts for
5 papers · 1 filter
Multi-domain semantic segmentation with overlapping labels
Petra Bevandić, Marin Oršić, Ivan Grubišić +2
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degr…
Revisiting consistency for semi-supervised semantic segmentation
Ivan Grubišić, Marin Oršić, Siniša Šegvić
Semi-supervised learning an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of…
Densely connected normalizing flows
Matej Grcić, Ivan Grubišić, Siniša Šegvić
Normalizing flows are bijective mappings between inputs and latent representations with a fully factorized distribution. They are very attractive due to exact likelihood valuation…
Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
Josip Šarić, Sacha Vražić, Siniša Šegvić
Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to va…
Dense outlier detection and open-set recognition based on training with noisy negative images
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently b…