Sergey Zagoruyko — accepted AI-conference papers

2025

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip, Valentin Malykh, Stamatios Lefkimmiatis, Nikos Komodakis +1

NeurIPS 2025poster

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning…

Cited by 0 Source ↗code ↗Scholar ↗

2024

PairDETR : Joint Detection and Association of Human Bodies and Faces

Ammar Ali, Georgii Gaikov, Denis Rybalchenko, Alexander Chigorin, Ivan Laptev, Sergey Zagoruyko

CVPR 2024poster

Image and video analysis requires not only accurate object but also the understanding of relationships among detected objects. Common solutions to relation modeling typically resort to stand-alone object detectors followed by non-differentiable post-processing techniques. Recently introduced detecti…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of Experts

Stefano Pini, Christian S. Perone, Aayush Ahuja, Ana Sofia Rufino Ferreira, Moritz Niendorf, Sergey Zagoruyko

ICRA 2023poster

The goal of autonomous vehicles is to navigate public roads safely and comfortably. To enforce safety, traditional planning approaches rely on handcrafted rules to generate trajectories. Machine learning-based systems, on the other hand, scale with data and are able to learn more complex behaviors.…

Cited by 45 Source ↗Scholar ↗

2023

Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking

Ziqi Pang, Jie Li, Pavel Tokmakov, Dian Chen, Sergey Zagoruyko, Yu-Xiong Wang

CVPR 2023poster

This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning for Tracking" (PF-Track). Specifically, our method adapts th…

Cited by 59 Source ↗PDF ↗code ↗Scholar ↗

2020

End-to-End Object Detection with Transformers

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko

ECCV 2020poster

We present a new method that views object detection as a direct set prediction. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge ab…

Cited by 17886 Source ↗PDF ↗code ↗Scholar ↗

2020

Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning

Yann Labbé, Sergey Zagoruyko, Igor Kalevatykh, Ivan Laptev, Justin Carpentier, Mathieu Aubry +1

RA-L 2020

We address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming from an RGB camera. To do so, we introduce a complete pipeline

Cited by 82 Source ↗code ↗Scholar ↗

2018

Compressing the Input for CNNs with the First-Order Scattering Transform

Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko, Michal Valko

ECCV 2018poster

We consider the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We study this transformation and show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this t…

Cited by 42 Source ↗PDF ↗code ↗Scholar ↗

2017

Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

Sergey Zagoruyko, Nikos Komodakis

ICLR 2017poster

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that…

Cited by 3439 Source ↗code ↗Scholar ↗

2017

Scaling the Scattering Transform: Deep Hybrid Networks

Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko

ICCV 2017poster

We use the scattering network as a generic and fixed initialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providing the best results to-date with pre-defined representations while being competitive with Deep CNNs. Us…

Cited by 171 PDF ↗code ↗Scholar ↗

2015

A MRF Shape Prior for Facade Parsing With Occlusions

Mateusz Kozinski, Raghudeep Gadde, Sergey Zagoruyko, Guillaume Obozinski, Renaud Marlet

CVPR 2015poster

We present a new shape prior formalism for segmentation of rectified facade images. It combines the simplicity of split grammars with unprecedented expressive power: the capability of encoding simultaneous alignment in two dimensions, facade occlusions and irregular boundaries between facade element…

Cited by 52 Source ↗PDF ↗Scholar ↗

2015

Learning to Compare Image Patches via Convolutional Neural Networks

Sergey Zagoruyko, Nikos Komodakis

CVPR 2015poster

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-bas…

Cited by 1924 Source ↗PDF ↗code ↗Scholar ↗