Search Results for author:
Found 22 papers, 13 papers with code
Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis
This work presents Switti, a scale-wise transformer for text-to-image generation.
YaART: Yet Another ART Rendering Technology
In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier.
Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models
Finally, we show that our approach can adapt the pretrained model to the user-specified image and text description on the fly just for 4 seconds.
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Following this line of work, we propose a new hyperbolic-based model for metric learning.
Ranked #1 on
Metric Learning
on CUB-200-2011
Understanding DDPM Latent Codes Through Optimal Transport
Diffusion models have recently outperformed alternative approaches to model the distribution of natural images, such as GANs.
Label-Efficient Semantic Segmentation with Diffusion Models
Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance.
Latent Transformations via NeuralODEs for GAN-based Image Editing
Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN.
Revisiting Deep Learning Models for Tabular Data
The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets.
Neural Side-by-Side: Predicting Human Preferences for No-Reference Super-Resolution Evaluation
Given the dataset and the labels, we trained a CNN model that obtains a pair of images and for each image predicts a probability of being more preferable than its counterpart.
Disentangled Representations from Non-Disentangled Models
Constructing disentangled representations is known to be a difficult task, especially in the unsupervised scenario.
Functional Space Analysis of Local GAN Convergence
Recent work demonstrated the benefits of studying continuous-time dynamics governing the GAN training.
Tensorized Embedding Layers
The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing.
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem.
Sample Efficient Ensemble Learning with Catalyst.RL
We present Catalyst. RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research.
Universality Theorems for Generative Models
Despite the fact that generative models are extremely successful in practice, the theory underlying this phenomenon is only starting to catch up with practice.
Hyperbolic Image Embeddings
Computer vision tasks such as image classification, image retrieval and few-shot learning are currently dominated by Euclidean and spherical embeddings, so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity).
Tensorized Embedding Layers for Efficient Model Compression
The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing.
Generalized Tensor Models for Recurrent Neural Networks
Such networks, however, are not very often applied to real life tasks.
Geometry Score: A Method For Comparing Generative Adversarial Networks
One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse.
Tensor Train decomposition on TensorFlow (T3F)
Tensor Train decomposition is used across many branches of machine learning.
Mathematical Software Numerical Analysis
Expressive power of recurrent neural networks
In this paper, we prove the expressive power theorem (an exponential lower bound on the width of the equivalent shallow network) for a class of recurrent neural networks -- ones that correspond to the Tensor Train (TT) decomposition.
Art of singular vectors and universal adversarial perturbations
Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies.
