Juho Kannala

Juho Kannala

Auto-generated profile, based on publicly available information

Juho Kannala

Aalto University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Neural Networks
Verified
Journal Article
Open access
VVVikas Verma
Vikas Verma
KKKenji Kawaguchi
Kenji Kawaguchi
ALAlex Lamb
Alex Lamb
JKJuho Kannala
Juho Kannala
ASArno Solin
Arno Solin
DLDavid Lopez-Paz
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. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets. Our theoretical analysis shows that ICT corresponds to a certain type of data-adaptive regularization with unlabeled points which reduces overfitting to labeled points under high confidence values.

28 February 2020 in Science Advances
Verified
Journal Article
Open access
PDF file
BABenjamin Alldritt
Benjamin Alldritt
PHProkop Hapala
Prokop Hapala
NONiko Oinonen
Niko Oinonen
FUFedor Urtev
Fedor Urtev
OKOndrej Krejci
Ondrej Krejci
AFAdam S. Foster
Adam S. Foster
Atomic force microscopy (AFM) with molecule-functionalized tips has emerged as the primary experimental technique for probing the atomic structure of organic molecules on surfaces. Most experiments have been limited to nearly planar aromatic molecules due to difficulties with interpretation of highly distorted AFM images originating from nonplanar molecules. Here, we develop a deep learning infrastructure that matches a set of AFM images with a unique descriptor characterizing the molecular configuration, allowing us to predict the molecular structure directly. We apply this methodology to resolve several distinct adsorption configurations of 1S-camphor on Cu(111) based on low-temperature AFM measurements. This approach will open the door to applying high-resolution AFM to a large variety of systems, for which routine atomic and chemical structural resolution on the level of individual objects/molecules would be a major breakthrough.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
SCSantiago Cortés
Santiago Cortés
ASArno Solin
Arno Solin
EREsa Rahtu
Esa Rahtu
JKJuho Kannala
Juho Kannala

6 February 2024 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
SWShuzhe Wang
Shuzhe Wang
ZLZakaria Laskar
Zakaria Laskar
IMIaroslav Melekhov
Iaroslav Melekhov
XLXiaotian Li
Xiaotian Li
YZYi Zhao
Yi Zhao
JKJuho Kannala
Juho Kannala
Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. 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. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image localization on the 7-Scenes, 12-Scenes, Cambridge Landmarks datasets, and the combined indoor scenes.

16 July 2022 in Neural Networks
Verified
Journal Article
Open access
ALAlex Lamb
Alex Lamb
VVVikas Verma
Vikas Verma
KKKenji Kawaguchi
Kenji Kawaguchi
AMAlexander Matyasko
Alexander Matyasko
SKSavya Khosla
Savya Khosla
YBYoshua BENGIO
Yoshua BENGIO
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how the adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve accuracy on the unperturbed data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial training. On CIFAR-10, adversarial training increases the standard test error ( when there is no adversary) from 4.43% to 12.32%, whereas with our Interpolated adversarial training we retain the adversarial robustness while achieving a standard test error of only 6.45%. With our technique, the relative increase in the standard error for the robust model is reduced from 178.1% to just 45.5%. Moreover, we provide mathematical analysis of Interpolated Adversarial Training to confirm its efficiencies and demonstrate its advantages in terms of robustness and generalization.

1 November 2024
Verified
Book Chapter
Closed access
PDF file
OSOtto Seiskari
Otto Seiskari
JYJerry Ylilammi
Jerry Ylilammi
VKValtteri Kaatrasalo
Valtteri Kaatrasalo
PRPekka Rantalankila
Pekka Rantalankila
MTMatias Turkulainen
Matias Turkulainen
ASArno Solin
Arno Solin