1 code implementation • 12 Apr 2024 • Xiaomeng Zhu, Talha Bilal, Pär Mårtensson, Lars Hanson, Mårten Björkman, Atsuto Maki
To this end, we introduce a synthetic dataset that may serve as a preliminary testbed for the Sim-to-Real challenge; it contains 17 objects of six industrial use cases, including isolated and assembled parts.
no code implementations • 20 Mar 2024 • Hiroki Azuma, Yusuke Matsui, Atsuto Maki
Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available.
no code implementations • 8 Apr 2023 • Marcus Nordström, Henrik Hult, Atsuto Maki
Based on recent work on loss function characterization, it is shown that optimal solutions to soft-Dice can be recovered by thresholding solutions to cross-entropy with a particular a priori unknown threshold that efficiently can be computed.
no code implementations • 3 Apr 2023 • Marcus Nordström, Henrik Hult, Atsuto Maki, Fredrik Löfman
This paper presents a study on the soft-Dice loss, one of the most popular loss functions in medical image segmentation, for situations where noise is present in target labels.
no code implementations • 31 Mar 2023 • Takumi Kanai, Naoya Sogi, Atsuto Maki, Kazuhiro Fukui
This paper proposes a new method for anomaly detection in time-series data by incorporating the concept of difference subspace into the singular spectrum analysis (SSA).
1 code implementation • 18 Oct 2022 • Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation.
no code implementations • 30 Sep 2022 • Vladimir Li, Atsuto Maki
In this paper, by explicitly modularising knowledge distillation into a framework of three components, i. e. affinity, normalisation, and loss, we give a unified treatment of these algorithms as well as study a number of unexplored combinations of the modules.
1 code implementation • 3 Jan 2022 • Miquel Martí i Rabadán, Sebastian Bujwid, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches.
no code implementations • 29 Oct 2019 • Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing-Hao Xue, Atsuto Maki
To avoid the difficulty, we first introduce geometrical Fisher discriminant analysis (gFDA) based on a simplified Fisher criterion.
no code implementations • CVPR 2020 • Yang Zhong, Atsuto Maki
That is, a CNN is efficiently regularized without additional resources of data or prior domain expertise.
no code implementations • 29 Jan 2019 • Di Feng, Xiao Wei, Lars Rosenbaum, Atsuto Maki, Klaus Dietmayer
Training a deep object detector for autonomous driving requires a huge amount of labeled data.
no code implementations • 2 Oct 2018 • Yang Zhong, Vladimir Li, Ryuzo Okada, Atsuto Maki
This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e. g., image classification, for efficiency as well as accuracy in transfer learning.
no code implementations • 31 Oct 2017 • Miquel Martí, Atsuto Maki
We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems.
3 code implementations • 15 Oct 2017 • Mateusz Buda, Atsuto Maki, Maciej A. Mazurowski
In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities.
no code implementations • 27 Jul 2016 • Ali Ghadirzadeh, Judith Bütepage, Atsuto Maki, Danica Kragic, Mårten Björkman
Modeling of physical human-robot collaborations is generally a challenging problem due to the unpredictive nature of human behavior.
no code implementations • 20 Dec 2014 • Ali Sharif Razavian, Josephine Sullivan, Stefan Carlsson, Atsuto Maki
This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval.
no code implementations • 24 Nov 2014 • Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, Stefan Carlsson
Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or the variation within the object class.
no code implementations • 22 Jun 2014 • Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson
In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target).