Search Results for author: Anton Konushin

Found 28 papers, 16 papers with code

Features Fusion for Dual-View Mammography Mass Detection

no code implementations25 Apr 2024 Arina Varlamova, Valery Belotsky, Grigory Novikov, Anton Konushin, Evgeny Sidorov

Detection of malignant lesions on mammography images is extremely important for early breast cancer diagnosis.

Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data

no code implementations CVPR 2022 Nikolay Patakin, Mikhail Romanov, Anna Vorontsova, Mikhail Artemyev, Anton Konushin

On the contrary, we propose GP$^{2}$, General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting.

3D Reconstruction Depth Estimation +1

Independent Component Alignment for Multi-Task Learning

1 code implementation CVPR 2023 Dmitry Senushkin, Nikolay Patakin, Arseny Kuznetsov, Anton Konushin

In this work, we propose using a condition number of a linear system of gradients as a stability criterion of an MTL optimization.

Depth Estimation Instance Segmentation +3

Contour-based Interactive Segmentation

no code implementations13 Feb 2023 Danil Galeev, Polina Popenova, Anna Vorontsova, Anton Konushin

Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly.

Interactive Segmentation Segmentation

TR3D: Towards Real-Time Indoor 3D Object Detection

1 code implementation6 Feb 2023 Danila Rukhovich, Anna Vorontsova, Anton Konushin

Our model with early feature fusion, which we refer to as TR3D+FF, outperforms existing 3D object detection approaches on the SUN RGB-D dataset.

3D Object Detection Object +1

Top-Down Beats Bottom-Up in 3D Instance Segmentation

1 code implementation6 Feb 2023 Maksim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich

Most 3D instance segmentation methods exploit a bottom-up strategy, typically including resource-exhaustive post-processing.

Ranked #5 on 3D Instance Segmentation on S3DIS (using extra training data)

3D Instance Segmentation Segmentation +1

Floorplan-Aware Camera Poses Refinement

no code implementations10 Oct 2022 Anna Sokolova, Filipp Nikitin, Anna Vorontsova, Anton Konushin

Processing large indoor scenes is a challenging task, as scan registration and camera trajectory estimation methods accumulate errors across time.

3D Reconstruction Model Optimization

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

3 code implementations1 Dec 2021 Danila Rukhovich, Anna Vorontsova, Anton Konushin

Existing 3D object detection methods make prior assumptions on the geometry of objects, and we argue that it limits their generalization ability.

3D Object Detection Object +1

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

6 code implementations12 Feb 2021 Konstantin Sofiiuk, Ilia A. Petrov, Anton Konushin

We find that the models trained on a combination of COCO and LVIS with diverse and high-quality annotations show performance superior to all existing models.

Interactive Segmentation Segmentation

Towards General Purpose Geometry-Preserving Single-View Depth Estimation

1 code implementation25 Sep 2020 Mikhail Romanov, Nikolay Patatkin, Anna Vorontsova, Sergey Nikolenko, Anton Konushin, Dmitry Senyushkin

Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.

Diversity Monocular Depth Estimation +1

Learning High-Resolution Domain-Specific Representations with a GAN Generator

1 code implementation18 Jun 2020 Danil Galeev, Konstantin Sofiiuk, Danila Rukhovich, Mikhail Romanov, Olga Barinova, Anton Konushin

Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.

Decoder Diversity +2

Foreground-aware Semantic Representations for Image Harmonization

1 code implementation1 Jun 2020 Konstantin Sofiiuk, Polina Popenova, Anton Konushin

Image harmonization is an important step in photo editing to achieve visual consistency in composite images by adjusting the appearances of foreground to make it compatible with background.

Decoder Image Harmonization

Decoder Modulation for Indoor Depth Completion

1 code implementation18 May 2020 Dmitry Senushkin, Mikhail Romanov, Ilia Belikov, Anton Konushin, Nikolay Patakin

Our second contribution is a novel training strategy that allows us to train on a semi-dense sensor data when the ground truth depth map is not available.

Decoder Depth Completion +2

IterDet: Iterative Scheme for Object Detection in Crowded Environments

1 code implementation12 May 2020 Danila Rukhovich, Konstantin Sofiiuk, Danil Galeev, Olga Barinova, Anton Konushin

Deep learning-based detectors usually produce a redundant set of object bounding boxes including many duplicate detections of the same object.

Object object-detection +1

f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

3 code implementations CVPR 2020 Konstantin Sofiiuk, Ilia Petrov, Olga Barinova, Anton Konushin

We propose f-BRS (feature backpropagating refinement scheme) that solves an optimization problem with respect to auxiliary variables instead of the network inputs, and requires running forward and backward pass just for a small part of a network.

Interactive Segmentation Segmentation

Training Deep SLAM on Single Frames

1 code implementation11 Dec 2019 Igor Slinko, Anna Vorontsova, Dmitry Zhukov, Olga Barinova, Anton Konushin

We train visual odometry model on synthetic data and do not use ground truth poses hence this model can be considered unsupervised.

Optical Flow Estimation Visual Odometry

Perceptual Image Anomaly Detection

2 code implementations12 Sep 2019 Nina Tuluptceva, Bart Bakker, Irina Fedulova, Anton Konushin

We present a novel method for image anomaly detection, where algorithms that use samples drawn from some distribution of "normal" data, aim to detect out-of-distribution (abnormal) samples.

Anomaly Detection Image Reconstruction

Scene Motion Decomposition for Learnable Visual Odometry

no code implementations16 Jul 2019 Igor Slinko, Anna Vorontsova, Filipp Konokhov, Olga Barinova, Anton Konushin

Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene.

Motion Estimation Optical Flow Estimation +1

Pose-based Deep Gait Recognition

no code implementations17 Oct 2017 Anna Sokolova, Anton Konushin

In this paper, we present a new pose-based convolutional neural network model for gait recognition.

Gait Recognition Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.