Andrei Atanov

I am a PhD student at VILAB, EPFL, supervised by Amir Zamir. My research is broadly focused on building deep learning systems that can perceive, understand and act in the world. Previously I was a junior researcher at BayesGroup and Samsung-HSE Lab, supervised by Dmitry Vetrov. I received my bachelor's and master's degree in Computer Science from the HSE University.

📧 Email  /  📋 CV  /  🎓 Google Scholar  /  🧑‍💻 GitHub  /  🐦 Twitter

How far can a 1-pixel camera go? This project explores solving different vision tasks using a simple photoreceptor (think 1-pixel camera) instead of a high-resolution camera. We find that 1) such simple sensors can solve different vision tasks and 2) their design (e.g., placement) is crucial for their effectiveness.

We propose a method to generate synthetic training data specifically useful for a given supervised model and image domain. We introduce two feedback mechanisms to guide the generation: 1) model-based and 2) target distribution-based.

Co-organized a tutorial on computational design.

We study the key components of diversification methods that were recently shown to achieve state-of-the-art OOD generalization. We show: 1) they are sensitive to the distribution of unlabeled data, 2) diversification alone is insufficient for OOD generalization and the right learning algorithm is needed and 3) the choice of the learning algorithm and the unlabeled data distribution are co-dependent.

What are the tasks a neural network can generalize on? How do they look, and what do they indicate? We introduce a task discovery framework to approach these questions empirically. These tasks reflect the inductive biases of NNs learned with SGD and can shed more light on how they generalize. Or do not! We show how one can use these tasks to reveal the failure modes of NNs via creating adversarial train-test data partitions.

A new pre-training method that captures and leverages cross-modal interactions.

3DCC is a set of more realistic 3D corruptions that can be used as a benchmark or data augmentations.

We propose a flexible prior distribution over convolutional kernels of Bayesian neural networks.

We apply conditional normalizing flows to semi-supervised learning. We utilize multiscale architecture for computational efficiency.

We propose a probabilistic view on Batch Normalization and an efficient test-time averaging technique for uncertainty estimation in batch-normalized DNNs.

Credits to Jon Barron for the template.