Search Results for author:
Found 19 papers, 4 papers with code
Image Vectorization: a Review
Vectorization is the process of converting a raster image into a similar vector image using primitive shapes.
Neural Style Transfer for Vector Graphics
We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image.
Multi-step domain adaptation by adversarial attack to $\mathcal{H} Δ\mathcal{H}$-divergence
Adversarial examples are transferable between different models.
Connecting adversarial attacks and optimal transport for domain adaptation
In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain.
Conditional Vector Graphics Generation for Music Cover Images
As almost all the existing image synthesis algorithms consider an image as a pixel matrix, the high-resolution image synthesis is complicated. A good alternative can be vector images.
Cycle monotonicity of adversarial attacks for optimal domain adaptation
In our algorithm, instead of mapping from target to the source domain, optimal transport maps target samples to the set of adversarial examples.
Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling
According to recent studies, commonly used computer vision datasets contain about 4% of label errors.
Two-Faced Humans on Twitter and Facebook: Harvesting Social Multimedia for Human Personality Profiling
We have also found that the selection of a machine learning approach is of crucial importance when choosing social network data sources and that people tend to reveal multiple facets of their personality in different social media avenues.
Solving Continuous Control with Episodic Memory
The application of episodic memory for continuous control with a large action space is not trivial.
SoMin.ai: Personality-Driven Content Generation Platform
Guided by the MBTI personality type, automatically derived from a user social network content, SoMin. ai generates new social media content based on the preferences of other users with a similar personality type aiming at enhancing the user experience on social networking venues as well diversifying the efforts of marketers when crafting new content for digital marketing campaigns.
Stabilizing Transformer-Based Action Sequence Generation For Q-Learning
To support the findings of this work, this paper seeks to provide an additional example of a Transformer-based RL method.
I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance
Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks.
Conditioning of Reinforcement Learning Agents and its Policy Regularization Application
In this paper, we try to answer the following question: Can information about policy conditioning help to shape a more stable and general policy of reinforcement learning agents?
Interpretable Few-Shot Learning via Linear Distillation
It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions.
Learning to Generate Chairs with Generative Adversarial Nets
In particular, it does not allow to train convolutional GAN models with fully-connected hidden layers.
Towards Never Ending Language Learning for Morphologically Rich Languages
This work deals with ontology learning from unstructured Russian text.
Reinforcement Learning Approach for Parallelization in Filters Aggregation Based Feature Selection Algorithms
One of the classical problems in machine learning and data mining is feature selection.
Reinforcement-based Simultaneous Algorithm and its Hyperparameters Selection
In this paper, we present a new method for the simultaneous selection of an algorithm and its hyperparameters.
