Search Results for author: Juho Kannala

Found 76 papers, 38 papers with code

MixupE: Understanding and Improving Mixup from Directional Derivative Perspective

no code implementations27 Dec 2022 Vikas Verma, Sarthak Mittal, Wai Hoh Tang, Hieu Pham, Juho Kannala, Yoshua Bengio, Arno Solin, Kenji Kawaguchi

Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels.

Data Augmentation

SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation and Prediction

1 code implementation28 Nov 2022 Hao Dong, Xianjing Zhang, Xuan Jiang, Jun Zhang, Jintao Xu, Rui Ai, Weihao Gu, Huimin Lu, Juho Kannala, Xieyuanli Chen

To this end, we propose a novel network named SuperFusion, exploiting the fusion of LiDAR and camera data at multiple levels.

Autonomous Driving

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

1 code implementation25 Oct 2022 Yi Zhao, Rinu Boney, Alexander Ilin, Juho Kannala, Joni Pajarinen

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment.

D4RL Offline RL +2

Continuous Monte Carlo Graph Search

no code implementations4 Oct 2022 Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen

To solve this problem, this paper proposes Continuous Monte Carlo Graph Search (CMCGS), a novel extension of MCTS to online planning in environments with continuous state and action spaces.

Decision Making

Uncertainty-guided Source-free Domain Adaptation

1 code implementation16 Aug 2022 Subhankar Roy, Martin Trapp, Andrea Pilzer, Juho Kannala, Nicu Sebe, Elisa Ricci, Arno Solin

Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model.

Source-Free Domain Adaptation

Visual Localization via Few-Shot Scene Region Classification

1 code implementation14 Aug 2022 Siyan Dong, Shuzhe Wang, Yixin Zhuang, Juho Kannala, Marc Pollefeys, Baoquan Chen

Visual (re)localization addresses the problem of estimating the 6-DoF (Degree of Freedom) camera pose of a query image captured in a known scene, which is a key building block of many computer vision and robotics applications.

General Classification Memorization +2

Disentangling Model Multiplicity in Deep Learning

no code implementations17 Jun 2022 Ari Heljakka, Martin Trapp, Juho Kannala, Arno Solin

This observed 'predictive' multiplicity (PM) also implies elusive differences in the internals of the models, their 'representational' multiplicity (RM).

Bridging the gap between paired and unpaired medical image translation

no code implementations15 Oct 2021 Pauliina Paavilainen, Saad Ullah Akram, Juho Kannala

Medical image translation has the potential to reduce the imaging workload, by removing the need to capture some sequences, and to reduce the annotation burden for developing machine learning methods.


Digging Into Self-Supervised Learning of Feature Descriptors

no code implementations10 Oct 2021 Iaroslav Melekhov, Zakaria Laskar, Xiaotian Li, Shuzhe Wang, Juho Kannala

Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks.

Image-Based Localization Image Retrieval +3

Independent Component Alignment for Multi-task Learning

no code implementations29 Sep 2021 Dmitry Senushkin, Iaroslav Melekhov, Mikhail Romanov, Anton Konushin, Juho Kannala, Arno Solin

We present a novel gradient-based multi-task learning (MTL) approach that balances training in multi-task systems by aligning the independent components of the training objective.

Camera Relocalization Multi-Label Image Classification +2

Continual Learning for Image-Based Camera Localization

1 code implementation ICCV 2021 Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Juho Kannala

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component.

Autonomous Driving Camera Localization +2

HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry

1 code implementation22 Jun 2021 Otto Seiskari, Pekka Rantalankila, Juho Kannala, Jerry Ylilammi, Esa Rahtu, Arno Solin

We present HybVIO, a novel hybrid approach for combining filtering-based visual-inertial odometry (VIO) with optimization-based SLAM.

Learning of feature points without additional supervision improves reinforcement learning from images

2 code implementations15 Jun 2021 Rinu Boney, Alexander Ilin, Juho Kannala

In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene.

Continuous Control reinforcement-learning +2

Single Source One Shot Reenactment using Weighted motion From Paired Feature Points

no code implementations7 Apr 2021 Soumya Tripathy, Juho Kannala, Esa Rahtu

Image reenactment is a task where the target object in the source image imitates the motion represented in the driving image.

Face Reenactment Image Animation

Novel View Synthesis via Depth-guided Skip Connections

1 code implementation5 Jan 2021 Yuxin Hou, Arno Solin, Juho Kannala

Flow predictions enable the target view to re-use pixels directly, but can easily lead to distorted results.

Novel View Synthesis

Learning to Play Imperfect-Information Games by Imitating an Oracle Planner

1 code implementation22 Dec 2020 Rinu Boney, Alexander Ilin, Juho Kannala, Jarno Seppänen

We experimentally show that planning with naive Monte Carlo tree search does not perform very well in large combinatorial action spaces.

Thompson Sampling

FACEGAN: Facial Attribute Controllable rEenactment GAN

no code implementations9 Nov 2020 Soumya Tripathy, Juho Kannala, Esa Rahtu

However, if the identity differs, the driving facial structures leak to the output distorting the reenactment result.

Face Reenactment

Movement-induced Priors for Deep Stereo

1 code implementation18 Oct 2020 Yuxin Hou, Muhammad Kamran Janjua, Juho Kannala, Arno Solin

We propose a method for fusing stereo disparity estimation with movement-induced prior information.

Disparity Estimation Stereo Disparity Estimation

Can You Trust Your Pose? Confidence Estimation in Visual Localization

no code implementations1 Oct 2020 Luca Ferranti, Xiaotian Li, Jani Boutellier, Juho Kannala

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations.

Autonomous Navigation Pose Estimation +1

Image Stylization for Robust Features

no code implementations16 Aug 2020 Iaroslav Melekhov, Gabriel J. Brostow, Juho Kannala, Daniyar Turmukhambetov

Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks.

Autonomous Driving Image Stylization +1

Data-Efficient Ranking Distillation for Image Retrieval

no code implementations10 Jul 2020 Zakaria Laskar, Juho Kannala

In low training sample settings, our approach outperforms the fully supervised approach on two challenging image retrieval datasets, ROxford5k and RParis6k \cite{Roxf} with the least possible teacher supervision.

Image Retrieval Knowledge Distillation +2

Interpolation-based semi-supervised learning for object detection

1 code implementation CVPR 2021 Jisoo Jeong, Vikas Verma, Minsung Hyun, Juho Kannala, Nojun Kwak

Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much.

object-detection Object Detection

Sensor Networks TDOA Self-Calibration: 2D Complexity Analysis and Solutions

no code implementations20 May 2020 Luca Ferranti, Kalle Åström, Magnus Oskarsson, Jani Boutellier, Juho Kannala

Given a network of receivers and transmitters, the process of determining their positions from measured pseudoranges is known as network self-calibration.

Deep Automodulators

2 code implementations NeurIPS 2020 Ari Heljakka, Yuxin Hou, Juho Kannala, Arno Solin

These networks can faithfully reproduce individual real-world input images like regular autoencoders, but also generate a fused sample from an arbitrary combination of several such images, allowing instantaneous 'style-mixing' and other new applications.


Regularizing Model-Based Planning with Energy-Based Models

no code implementations12 Oct 2019 Rinu Boney, Juho Kannala, Alexander Ilin

Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data.

Continuous Control Model-based Reinforcement Learning

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

1 code implementation25 Sep 2019 Vikas Verma, Meng Qu, Kenji Kawaguchi, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.

Generalization Bounds Graph Attention +1

GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning

no code implementations25 Sep 2019 Vikas Verma, Meng Qu, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang

We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks.

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

no code implementations CVPR 2020 Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.

Classification Data Augmentation +3

Iterative Path Reconstruction for Large-Scale Inertial Navigation on Smartphones

no code implementations2 Jun 2019 Santiago Cortés Reina, Yuxin Hou, Juho Kannala, Arno Solin

Modern smartphones have all the sensing capabilities required for accurate and robust navigation and tracking.

Motion Estimation

DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction

2 code implementations25 May 2019 Hamed R. -Tavakoli, Ali Borji, Esa Rahtu, Juho Kannala

Our results suggest that (1) audio is a strong contributing cue for saliency prediction, (2) salient visible sound-source is the natural cause of the superiority of our Audio-Visual model, (3) richer feature representations for the input space leads to more powerful predictions even in absence of more sophisticated saliency decoders, and (4) Audio-Visual model improves over 53. 54\% of the frames predicted by the best Visual model (our baseline).

Saliency Prediction Video Saliency Prediction

Geometric Image Correspondence Verification by Dense Pixel Matching

no code implementations15 Apr 2019 Zakaria Laskar, Iaroslav Melekhov, Hamed R. -Tavakoli, Juha Ylioinas, Juho Kannala

The main contribution is a geometric correspondence verification approach for re-ranking a shortlist of retrieved database images based on their dense pair-wise matching with the query image at a pixel level.

Image Retrieval Re-Ranking +2

Multi-View Stereo by Temporal Nonparametric Fusion

1 code implementation ICCV 2019 Yuxin Hou, Juho Kannala, Arno Solin

The flexibility of the Gaussian process (GP) prior provides adapting memory for fusing information from previous views.

Depth Estimation Disparity Estimation

Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders

1 code implementation12 Apr 2019 Ari Heljakka, Arno Solin, Juho Kannala

retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs.

Disentanglement Image Manipulation

Digging Deeper into Egocentric Gaze Prediction

no code implementations12 Apr 2019 Hamed R. -Tavakoli, Esa Rahtu, Juho Kannala, Ali Borji

Extensive experiments over multiple datasets reveal that (1) spatial biases are strong in egocentric videos, (2) bottom-up saliency models perform poorly in predicting gaze and underperform spatial biases, (3) deep features perform better compared to traditional features, (4) as opposed to hand regions, the manipulation point is a strong influential cue for gaze prediction, (5) combining the proposed recurrent model with bottom-up cues, vanishing points and, in particular, manipulation point results in the best gaze prediction accuracy over egocentric videos, (6) the knowledge transfer works best for cases where the tasks or sequences are similar, and (7) task and activity recognition can benefit from gaze prediction.

Activity Recognition Gaze Prediction +2

ICface: Interpretable and Controllable Face Reenactment Using GANs

1 code implementation3 Apr 2019 Soumya Tripathy, Juho Kannala, Esa Rahtu

This paper presents a generic face animator that is able to control the pose and expressions of a given face image.

Face Reenactment

CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis

1 code implementation3 Apr 2019 Ahti Kalervo, Juha Ylioinas, Markus Häikiö, Antti Karhu, Juho Kannala

Better understanding and modelling of building interiors and the emergence of more impressive AR/VR technology has brought up the need for automatic parsing of floorplan images.

Interpolation Consistency Training for Semi-Supervised Learning

4 code implementations9 Mar 2019 Vikas Verma, Kenji Kawaguchi, Alex Lamb, Juho Kannala, Arno Solin, Yoshua Bengio, David Lopez-Paz

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.

General Classification Semi-Supervised Image Classification

Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane Representation

1 code implementation6 Feb 2019 Yuxin Hou, Arno Solin, Juho Kannala

This paper presents a novel method, MaskMVS, to solve depth estimation for unstructured multi-view image-pose pairs.

Depth Estimation

Mask-RCNN and U-net Ensembled for Nuclei Segmentation

3 code implementations29 Jan 2019 Aarno Oskar Vuola, Saad Ullah Akram, Juho Kannala

Nuclei segmentation is both an important and in some ways ideal task for modern computer vision methods, e. g. convolutional neural networks.

Semantic Matching by Weakly Supervised 2D Point Set Registration

no code implementations24 Jan 2019 Zakaria Laskar, Hamed R. -Tavakoli, Juho Kannala

The problem is posed as finding the geometric transformation that aligns a given image pair.

Semi-Supervised Semantic Matching

no code implementations24 Jan 2019 Zakaria Laskar, Juho Kannala

Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images.

LSD$_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs

no code implementations23 Nov 2018 Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä, Janne Heikkilä

The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions.

Deblurring Denoising

Gyroscope-Aided Motion Deblurring with Deep Networks

1 code implementation1 Oct 2018 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).


Deep Learning Based Speed Estimation for Constraining Strapdown Inertial Navigation on Smartphones

1 code implementation10 Aug 2018 Santiago Cortés, Arno Solin, Juho Kannala

Strapdown inertial navigation systems are sensitive to the quality of the data provided by the accelerometer and gyroscope.

Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection

no code implementations31 Jul 2018 Saad Ullah Akram, Talha Qaiser, Simon Graham, Juho Kannala, Janne Heikkilä, Nasir Rajpoot

In this paper, we present a semi-supervised mitosis detection method which is designed to leverage a large number of unlabeled breast cancer WSIs.

Mitosis Detection whole slide images

ADVIO: An authentic dataset for visual-inertial odometry

1 code implementation ECCV 2018 Santiago Cortés, Arno Solin, Esa Rahtu, Juho Kannala

The lack of realistic and open benchmarking datasets for pedestrian visual-inertial odometry has made it hard to pinpoint differences in published methods.

Learning Representations for Soft Skill Matching

2 code implementations20 Jul 2018 Luiza Sayfullina, Eric Malmi, Juho Kannala

The disambiguation is formulated as a binary text classification problem where the prediction is made for the potential soft skill based on the context where it occurs.

Binary text classification text-classification +1

Pioneer Networks: Progressively Growing Generative Autoencoder

1 code implementation9 Jul 2018 Ari Heljakka, Arno Solin, Juho Kannala

Instead, we propose the Progressively Growing Generative Autoencoder (PIONEER) network which achieves high-quality reconstruction with $128{\times}128$ images without requiring a GAN discriminator.

Image Generation

Robust Gyroscope-Aided Camera Self-Calibration

1 code implementation31 May 2018 Santiago Cortés Reina, Arno Solin, Juho Kannala

This application paper proposes a model for estimating the parameters on the fly by fusing gyroscope and camera data, both readily available in modern day smartphones.

Camera Calibration Video Stabilization

Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements

no code implementations22 May 2018 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

It is well-known that motion blur decreases the performance of traditional feature detectors and descriptors.


Learning image-to-image translation using paired and unpaired training samples

1 code implementation8 May 2018 Soumya Tripathy, Juho Kannala, Esa Rahtu

In this paper, we propose a new general purpose image-to-image translation model that is able to utilize both paired and unpaired training data simultaneously.

Image-to-Image Translation Translation

Accurate 3-D Reconstruction with RGB-D Cameras using Depth Map Fusion and Pose Refinement

no code implementations24 Apr 2018 Markus Ylimäki, Juho Kannala, Janne Heikkilä

Then, the original depth maps are re-registered to the fused point cloud to refine the original camera extrinsic parameters.

Devon: Deformable Volume Network for Learning Optical Flow

no code implementations20 Feb 2018 Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions.

Optical Flow Estimation

Recursive Chaining of Reversible Image-to-image Translators For Face Aging

2 code implementations14 Feb 2018 Ari Heljakka, Arno Solin, Juho Kannala

By treating the age phases as a sequence of image domains, we construct a chain of transformers that map images from one age domain to the next.


Full-Frame Scene Coordinate Regression for Image-Based Localization

no code implementations9 Feb 2018 Xiaotian Li, Juha Ylioinas, Juho Kannala

In this paper, instead of in a patch-based manner, we propose to perform the scene coordinate regression in a full-frame manner to make the computation efficient at test time and, more importantly, to add more global context to the regression process to improve the robustness.

Camera Relocalization Data Augmentation +2

Image Patch Matching Using Convolutional Descriptors with Euclidean Distance

no code implementations31 Oct 2017 Iaroslav Melekhov, Juho Kannala, Esa Rahtu

In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications.

object-detection Object Detection +1

Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network

no code implementations31 Jul 2017 Zakaria Laskar, Iaroslav Melekhov, Surya Kalia, Juho Kannala

The camera location for the query image is obtained via triangulation from two relative translation estimates using a RANSAC based approach.

Camera Relocalization Pose Estimation

Cell Tracking via Proposal Generation and Selection

1 code implementation9 May 2017 Saad Ullah Akram, Juho Kannala, Lauri Eklund, Janne Heikkilä

Microscopy imaging plays a vital role in understanding many biological processes in development and disease.

Image-based Localization using Hourglass Networks

no code implementations23 Mar 2017 Iaroslav Melekhov, Juha Ylioinas, Juho Kannala, Esa Rahtu

In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGB-image.

General Classification Image-Based Localization +1

Context Aware Query Image Representation for Particular Object Retrieval

1 code implementation3 Mar 2017 Zakaria Laskar, Juho Kannala

Particularly, we show that by making the CNN pay attention on the ROI while extracting query image representation leads to significant improvement over the baseline methods on challenging Oxford5k and Paris6k datasets.

Image Retrieval Retrieval

Inertial Odometry on Handheld Smartphones

1 code implementation1 Mar 2017 Arno Solin, Santiago Cortes, Esa Rahtu, Juho Kannala

Building a complete inertial navigation system using the limited quality data provided by current smartphones has been regarded challenging, if not impossible.

Relative Camera Pose Estimation Using Convolutional Neural Networks

1 code implementation5 Feb 2017 Iaroslav Melekhov, Juha Ylioinas, Juho Kannala, Esa Rahtu

This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras.

General Classification Pose Estimation +2

Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices

1 code implementation29 Nov 2016 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

In the process, we also perform a temporal and spatial alignment of the camera and the IMU.

Real-time Human Pose Estimation from Video with Convolutional Neural Networks

no code implementations23 Sep 2016 Marko Linna, Juho Kannala, Esa Rahtu

In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks.

Action Recognition Pose Estimation

Understanding Objects in Detail with Fine-Grained Attributes

no code implementations CVPR 2014 Andrea Vedaldi, Siddharth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross Girshick, Juho Kannala, Esa Rahtu, Iasonas Kokkinos, Matthew B. Blaschko, David Weiss, Ben Taskar, Karen Simonyan, Naomi Saphra, Sammy Mohamed

We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object.

object-detection Object Detection

Fine-Grained Visual Classification of Aircraft

1 code implementation21 Jun 2013 Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, Andrea Vedaldi

This paper introduces FGVC-Aircraft, a new dataset containing 10, 000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy.

Classification Fine-Grained Image Classification +1

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