Search Results for author:
Found 49 papers, 32 papers with code
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.
QUASAR: QUality and Aesthetics Scoring with Advanced Representations
This paper introduces a new data-driven, non-parametric method for image quality and aesthetics assessment, surpassing existing approaches and requiring no prompt engineering or fine-tuning.
Extreme Compression of Large Language Models via Additive Quantization
The emergence of accurate open large language models (LLMs) has led to a race towards quantization techniques for such models enabling execution on end-user devices.
Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models
While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage.
TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023
Deep learning (DL) models for tabular data problems (e. g. classification, regression) are currently receiving increasingly more attention from researchers.
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.
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs.
Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics
Text-to-image generation models represent the next step of evolution in image synthesis, offering a natural way to achieve flexible yet fine-grained control over the result.
TabDDPM: Modelling Tabular Data with Diffusion Models
Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities.
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
For this, we formalize desirable properties for a proper homophily measure and verify which measures satisfy which properties.
Revisiting Pretraining Objectives for Tabular Deep Learning
Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT).
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
The outcome of the competition was ranked leaderboards of algorithms in each track based on recall at a query throughput threshold.
On Embeddings for Numerical Features in Tabular Deep Learning
We start by describing two conceptually different approaches to building embedding modules: the first one is based on a piecewise linear encoding of scalar values, and the second one utilizes periodic activations.
When, Why, and Which Pretrained GANs Are Useful?
The literature has proposed several methods to finetune pretrained GANs on new datasets, which typically results in higher performance compared to training from scratch, especially in the limited-data regime.
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.
Distilling the Knowledge from Conditional Normalizing Flows
Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems.
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.
Discovering Weight Initializers with Meta Learning
In this study, we propose a task-agnostic approach that discovers initializers for specific network architectures and optimizers by learning the initial weight distributions directly through the use of Meta-Learning.
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.
On Self-Supervised Image Representations for GAN Evaluation
The embeddings from CNNs pretrained on Imagenet classification are de-facto standard image representations for assessing GANs via FID, Precision and Recall measures.
Unsupervised Discovery of Interpretable Latent Manipulations in Language VAEs
In this work, we make the first step towards unsupervised discovery of interpretable directions in language latent spaces.
Navigating the GAN Parameter Space for Semantic Image Editing
In contrast to existing works, which mostly operate by latent codes, we discover interpretable directions in the space of the generator parameters.
Object Segmentation Without Labels with Large-Scale Generative Models
The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks.
Editable Neural Networks
We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
The latent spaces of GAN models often have semantically meaningful directions.
RPGAN: GANs Interpretability via Random Routing
In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis.
Towards Similarity Graphs Constructed by Deep Reinforcement Learning
New algorithms for similarity graph construction are continuously being proposed and analyzed by both theoreticians and practitioners.
Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
Our main contribution is PRODIGE: a method that learns a weighted graph representation of data end-to-end by gradient descent.
RPGAN: random paths as a latent space for GAN interpretability
In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) --- an alternative scheme of GANs that can serve as a tool for generative model analysis.
Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data
In this paper, we introduce Neural Oblivious Decision Ensembles (NODE), a new deep learning architecture, designed to work with any tabular data.
Relevance Proximity Graphs for Fast Relevance Retrieval
In plenty of machine learning applications, the most relevant items for a particular query should be efficiently extracted, while the relevance function is based on a highly-nonlinear model, e. g., DNNs or GBDTs.
Unsupervised Neural Quantization for Compressed-Domain Similarity Search
We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems.
Learning to Route in Similarity Graphs
Recently similarity graphs became the leading paradigm for efficient nearest neighbor search, outperforming traditional tree-based and LSH-based methods.
Non-metric Similarity Graphs for Maximum Inner Product Search
In this paper we address the problem of Maximum Inner Product Search (MIPS) that is currently the computational bottleneck in a large number of machine learning applications.
Impostor Networks for Fast Fine-Grained Recognition
In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on low-power and non-GPU enabled platforms.
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
This work addresses the problem of billion-scale nearest neighbor search.
AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding
To compress large datasets of high-dimensional descriptors, modern quantization schemes learn multiple codebooks and then represent individual descriptors as combinations of codewords.
Product Split Trees
In this work, we introduce a new kind of spatial partition trees for efficient nearest-neighbor search.
Pairwise Quantization
The proposed approach proceeds by finding a linear transformation of the data that effectively reduces the minimization of the pairwise distortions to the minimization of individual reconstruction errors.
Efficient Indexing of Billion-Scale Datasets of Deep Descriptors
In this paper, we introduce a new dataset of one billion descriptors based on DNNs and reveal the relative inefficiency of IMI-based indexing for such descriptors compared to SIFT data.
Aggregating Local Deep Features for Image Retrieval
Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems.
Ranked #15 on
Image Retrieval
on RParis (Hard)
Aggregating Deep Convolutional Features for Image Retrieval
In this paper we investigate possible ways to aggregate local deep features to produce compact global descriptors for image retrieval.
Ranked #15 on
Image Retrieval
on RParis (Medium)
Tree Quantization for Large-Scale Similarity Search and Classification
We propose a new vector encoding scheme (tree quantization) that obtains lossy compact codes for high-dimensional vectors via tree-based dynamic programming.
Additive Quantization for Extreme Vector Compression
We introduce a new compression scheme for high-dimensional vectors that approximates the vectors using sums of M codewords coming from M different codebooks.
Neural Codes for Image Retrieval
In the experiments with several standard retrieval benchmarks, we establish that neural codes perform competitively even when the convolutional neural network has been trained for an unrelated classification task (e. g.\ Image-Net).
Improving Bilayer Product Quantization for Billion-Scale Approximate Nearest Neighbors in High Dimensions
Here we introduce and evaluate two approximate nearest neighbor search systems that both exploit the synergy of product quantization processes in a more efficient way.
