VK

Valentin Khrulkov

Diffusion models, low-rank tensor decompositions, unsupervised and semisupervised learning, theoretical analysis of neural networks. Especially, I am interested in applications of various geometrical (differential, algebraic, topological) ideas and techniques to neural networks to further our understanding of deep learning.

Publications

  • Understanding DDPM Latent Codes Through Optimal Transport

    Machine learning theory
    Valentin Khrulkov
    Gleb Ryzhakov
    Andrei Chertkov
    Ivan Oseledets
    ICLR, 2023

    Diffusion models have recently outperformed alternative approaches to model the distribution of natural images. Such diffusion models allow for deterministic sampling via the probability flow ODE, giving rise to a latent space and an encoder map. While having important practical applications, such as the estimation of the likelihood, the theoretical properties of this map are not yet fully understood. In the present work, we partially address this question for the popular case of the VP-SDE (DDPM) approach. We show that, perhaps surprisingly, the DDPM encoder map coincides with the optimal transport map for common distributions; we support this claim by extensive numerical experiments using advanced tensor train solver for multidimensional Fokker-Planck equation. We provide additional theoretical evidence for the case of multivariate normal distributions.

  • Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

    Computer visionRanking
    Aleksandr Ermolov
    Leyla Mirvakhabova
    Valentin Khrulkov
    Nicu Sebe
    Ivan Oseledets
    CVPR, 2022

    Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations – usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric

  • Label-Efficient Semantic Segmentation with Diffusion Models

    Computer vision
    Dmitry Baranchuk
    Ivan Rubachev
    Andrey Voynov
    Valentin Khrulkov
    Artem Babenko
    ICLR, 2022

    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. The superior performance of diffusion models has made them an appealing tool in several applications, including inpainting, super-resolution, and semantic editing. In this paper, we demonstrate that diffusion models can also serve as an instrument for semantic segmentation, especially in the setup when labeled data is scarce. In particular, for several pretrained diffusion models, we investigate the intermediate activations from the networks that perform the Markov step of the reverse diffusion process. We show that these activations effectively capture the semantic information from an input image and appear to be excellent pixel-level representations for the segmentation problem. Based on these observations, we describe a simple segmentation method, which can work even if only a few training images are provided. Our approach significantly outperforms the existing alternatives on several datasets for the same amount of human supervision.

Posts