21 citations · 56 across the 14 of their papers we have counts for
15 papers
Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality
Kunal Pratap Singh, Ali Garjani, Rishubh Singh +6
Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications…
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Andrei Atanov, Jesse Allardice, Roman Bachmann +6
Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and…
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Rahul Ramachandran, Ali Garjani, Roman Bachmann +3
Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond question answering remains unclear.…
Large (Vision) Language Models are Unsupervised In-Context Learners
Artyom Gadetsky, Andrei Atanov, Yulun Jiang +4
Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation…
Solving Vision Tasks with Simple Photoreceptors Instead of Cameras
Andrei Atanov, Jiawei Fu, Rishubh Singh +3
A de facto standard in solving computer vision problems is to use a common high-resolution camera and choose its placement on an agent (i.e., position and orientation) based on hum…
Controlled Training Data Generation with Diffusion Models
Teresa Yeo, Andrei Atanov, Harold Benoit +4
We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and…
Unraveling the Key Components of OOD Generalization via Diversification
Harold Benoit, Liangze Jiang, Andrei Atanov +3
Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training…
Task Discovery: Finding the Tasks that Neural Networks Generalize on
Andrei Atanov, Andrei Filatov, Teresa Yeo +2
When developing deep learning models, we usually decide what task we want to solve then search for a model that generalizes well on the task. An intriguing question would be: what…
3D Common Corruptions and Data Augmentation
Oğuzhan Fatih Kar, Teresa Yeo, Andrei Atanov +1
We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural network…
MultiMAE: Multi-modal Multi-task Masked Autoencoders
Roman Bachmann, David Mizrahi, Andrei Atanov +1
We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optional…
Simple Control Baselines for Evaluating Transfer Learning
Andrei Atanov, Shijian Xu, Onur Beker +2
Transfer learning has witnessed remarkable progress in recent years, for example, with the introduction of augmentation-based contrastive self-supervised learning methods. While a…
Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations
Arsenii Ashukha, Andrei Atanov, Dmitry Vetrov
Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time,…
Semi-Conditional Normalizing Flows for Semi-Supervised Learning
Andrei Atanov, Alexandra Volokhova, Arsenii Ashukha +2
This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint dist…
The Deep Weight Prior
Andrei Atanov, Arsenii Ashukha, Kirill Struminsky +2
Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior dist…
Uncertainty Estimation via Stochastic Batch Normalization
Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov +2
In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximaze…