activity
20162020
most citedScaling Matters in Deep Structured-Prediction Models

1 citations · 1 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CV2020

OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features

Anton Osokin, Denis Sumin, Vasily Lomakin

In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detect…

cs.LG2019

Cost-Sensitive Training for Autoregressive Models

Irina Saparina, Anton Osokin

Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings add…

cs.LG20191 cited

Scaling Matters in Deep Structured-Prediction Models

Aleksandr Shevchenko, Anton Osokin

Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system…

cs.CV2018

Tube-CNN: Modeling temporal evolution of appearance for object detection in video

Tuan-Hung Vu, Anton Osokin, Ivan Laptev

Object detection in video is crucial for many applications. Compared to images, video provides additional cues which can help to disambiguate the detection problem. Our goal in thi…

stat.ML2018

Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models

Tatiana Shpakova, Francis Bach, Anton Osokin

We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, wh…

cs.CV2017

GANs for Biological Image Synthesis

Anton Osokin, Anatole Chessel, Rafael E. Carazo Salas +1

In this paper, we propose a novel application of Generative Adversarial Networks (GAN) to the synthesis of cells imaged by fluorescence microscopy. Compared to natural images, cell…