Search Results for author: Mikhail Romanov

Found 5 papers, 3 papers with code

Independent Component Alignment for Multi-task Learning

no code implementations29 Sep 2021 Dmitry Senushkin, Iaroslav Melekhov, Mikhail Romanov, Anton Konushin, Juho Kannala, Arno Solin

We present a novel gradient-based multi-task learning (MTL) approach that balances training in multi-task systems by aligning the independent components of the training objective.

Camera Relocalization Multi-Label Image Classification +2

Towards General Purpose Geometry-Preserving Single-View Depth Estimation

1 code implementation25 Sep 2020 Mikhail Romanov, Nikolay Patatkin, Anna Vorontsova, Sergey Nikolenko, Anton Konushin, Dmitry Senyushkin

Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.

Monocular Depth Estimation Scene Understanding

Learning High-Resolution Domain-Specific Representations with a GAN Generator

1 code implementation18 Jun 2020 Danil Galeev, Konstantin Sofiiuk, Danila Rukhovich, Mikhail Romanov, Olga Barinova, Anton Konushin

Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.

Semi-Supervised Semantic Segmentation

Decoder Modulation for Indoor Depth Completion

1 code implementation18 May 2020 Dmitry Senushkin, Mikhail Romanov, Ilia Belikov, Anton Konushin, Nikolay Patakin

Our second contribution is a novel training strategy that allows us to train on a semi-dense sensor data when the ground truth depth map is not available.

Depth Completion Depth Estimation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.