55 citations · 218 across the 22 of their papers we have counts for
6 papers · 1 filter
Pretraining a Neural Network before Knowing Its Architecture
Boris Knyazev
Training large neural networks is possible by training a smaller hypernetwork that predicts parameters for the large ones. A recently released Graph HyperNetwork (GHN) trained this…
Generative Compositional Augmentations for Scene Graph Prediction
Boris Knyazev, Harm de Vries, Cătălina Cangea +3
Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challe…
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
Boris Knyazev, Harm de Vries, Cătălina Cangea +3
Scene graph generation (SGG) aims to predict graph-structured descriptions of input images, in the form of objects and relationships between them. This task is becoming increasingl…
Image Classification with Hierarchical Multigraph Networks
Boris Knyazev, Xiao Lin, Mohamed R. Amer +1
Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data. Despite being general, GCNs are admittedly inferior to convolutional ne…
Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video
Boris Knyazev, Roman Shvetsov, Natalia Efremova +1
In this paper we describe a solution to our entry for the emotion recognition challenge EmotiW 2017. We propose an ensemble of several models, which capture spatial and audio featu…
Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks
Boris Knyazev, Erhardt Barth, Thomas Martinetz
In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the…