no code implementations • ECCV 2020 • Van Nhan Nguyen, Sigurd Løkse, Kristoffer Wickstrøm, Michael Kampffmeyer, Davide Roverso, Robert Jenssen
In this paper, we equip Prototypical Networks (PNs) with a novel dissimilarity measure to enable discriminative feature normalization for few-shot learning.
no code implementations • 25 Feb 2025 • Haoyuan Li, Yanpeng Zhou, Tao Tang, Jifei Song, Yihan Zeng, Michael Kampffmeyer, Hang Xu, Xiaodan Liang
However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images.
no code implementations • 3 Jun 2024 • Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer, Maurizio Filippone
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions.
no code implementations • 1 May 2024 • Xujie Zhang, Ente Lin, Xiu Li, Yuxuan Luo, Michael Kampffmeyer, Xin Dong, Xiaodan Liang
Besides, to remove the segmentation dependency, MMTryon uses a parsing-free garment encoder and leverages a novel scalable data generation pipeline to convert existing VITON datasets to a form that allows MMTryon to be trained without requiring any explicit segmentation.
1 code implementation • CVPR 2024 • Rwiddhi Chakraborty, Adrian Sletten, Michael Kampffmeyer
Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers.
no code implementations • 8 Dec 2023 • Ribana Roscher, Marc Rußwurm, Caroline Gevaert, Michael Kampffmeyer, Jefersson A. dos Santos, Maria Vakalopoulou, Ronny Hänsch, Stine Hansen, Keiller Nogueira, Jonathan Prexl, Devis Tuia
These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.
no code implementations • 6 Dec 2023 • Xujie Zhang, Xiu Li, Michael Kampffmeyer, Xin Dong, Zhenyu Xie, Feida Zhu, Haoye Dong, Xiaodan Liang
Image-based Virtual Try-On (VITON) aims to transfer an in-shop garment image onto a target person.
no code implementations • 2 Jul 2023 • Nanqing Dong, Zhipeng Wang, Jiahao Sun, Michael Kampffmeyer, William Knottenbelt, Eric Xing
In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy.
1 code implementation • 19 Jun 2023 • Sara Björk, Stian N. Anfinsen, Michael Kampffmeyer, Erik Næsset, Terje Gobakken, Lennart Noordermeer
These results are consistent for experiments on above-ground biomass prediction in Tanzania and stem volume prediction in Norway, representing a diversity in parameters and forest types that emphasises the robustness of the approach.
1 code implementation • 2 Mar 2023 • Luca Tomasetti, Stine Hansen, Mahdieh Khanmohammadi, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz, Michael Kampffmeyer
Precise ischemic lesion segmentation plays an essential role in improving diagnosis and treatment planning for ischemic stroke, one of the prevalent diseases with the highest mortality rate.
1 code implementation • 25 Nov 2022 • Zaiyu Huang, Hanhui Li, Zhenyu Xie, Michael Kampffmeyer, Qingling Cai, Xiaodan Liang
Existing methods are restricted in this setting as they estimate garment warping flows mainly based on 2D poses and appearance, which omits the geometric prior of the 3D human body shape.
1 code implementation • 15 Oct 2022 • Srishti Gautam, Ahcene Boubekki, Stine Hansen, Suaiba Amina Salahuddin, Robert Jenssen, Marina MC Höhne, Michael Kampffmeyer
The need for interpretable models has fostered the development of self-explainable classifiers.
no code implementations • 27 Jul 2022 • Zhenyu Xie, Zaiyu Huang, Fuwei Zhao, Haoye Dong, Michael Kampffmeyer, Xin Dong, Feida Zhu, Xiaodan Liang
In this work, we take a step forwards to explore versatile virtual try-on solutions, which we argue should possess three main properties, namely, they should support unsupervised training, arbitrary garment categories, and controllable garment editing.
no code implementations • 30 Jun 2022 • Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu
In the second stage, the decentralized partially labeled data are exploited to learn an energy-based multi-label classifier for the common classes.
1 code implementation • 18 May 2022 • Kristoffer Wickstrøm, J. Emmanuel Johnson, Sigurd Løkse, Gustau Camps-Valls, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen
Our proposed kernelized Taylor diagram is capable of visualizing similarities between populations with minimal assumptions of the data distributions.
no code implementations • 30 Mar 2022 • Jonas Lederer, Michael Gastegger, Kristof T. Schütt, Michael Kampffmeyer, Klaus-Robert Müller, Oliver T. Unke
In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular.
1 code implementation • 17 Mar 2022 • Kristoffer Wickstrøm, Michael Kampffmeyer, Karl Øyvind Mikalsen, Robert Jenssen
The lack of labeled data is a key challenge for learning useful representation from time series data.
1 code implementation • 3 Mar 2022 • Stine Hansen, Srishti Gautam, Robert Jenssen, Michael Kampffmeyer
Motivated by this, and the observation that the foreground class (e. g., one organ) is relatively homogeneous, we propose a novel anomaly detection-inspired approach to few-shot medical image segmentation in which we refrain from modeling the background explicitly.
no code implementations • 10 Jan 2022 • Srishti Gautam, Marina M. -C. Höhne, Stine Hansen, Robert Jenssen, Michael Kampffmeyer
The recent trend of integrating multi-source Chest X-Ray datasets to improve automated diagnostics raises concerns that models learn to exploit source-specific correlations to improve performance by recognizing the source domain of an image rather than the medical pathology.
1 code implementation • NeurIPS 2021 • Zhenyu Xie, Zaiyu Huang, Fuwei Zhao, Haoye Dong, Michael Kampffmeyer, Xiaodan Liang
Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential.
1 code implementation • 6 Nov 2021 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
To this end, we propose a new multi-modality network (MultiModNet) for land cover mapping of multi-modal remote sensing data based on a novel pyramid attention fusion (PAF) module and a gated fusion unit (GFU).
1 code implementation • 9 Oct 2021 • Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen
Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data.
no code implementations • 27 Aug 2021 • Srishti Gautam, Marina M. -C. Höhne, Stine Hansen, Robert Jenssen, Michael Kampffmeyer
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems.
1 code implementation • ICCV 2021 • Fuwei Zhao, Zhenyu Xie, Michael Kampffmeyer, Haoye Dong, Songfang Han, Tianxiang Zheng, Tao Zhang, Xiaodan Liang
Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.
1 code implementation • 20 May 2021 • Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu, Eric Xing
In this work, we provide some theoretical insight into the properties of QNNs by presenting and analyzing a new form of invariance embedded in QNNs for both quantum binary classification and quantum representation learning, which we term negational symmetry.
1 code implementation • CVPR 2021 • Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer
Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering.
1 code implementation • 7 Dec 2020 • Ahcène Boubekki, Michael Kampffmeyer, Robert Jenssen, Ulf Brefeld
That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding.
no code implementations • 28 Nov 2020 • Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Min Xu, Irina Voiculescu, Eric P. Xing
To bridge the methodological gaps in partially supervised learning (PSL) under data scarcity, we propose Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation.
1 code implementation • 16 Oct 2020 • Kristoffer Wickstrøm, Karl Øyvind Mikalsen, Michael Kampffmeyer, Arthur Revhaug, Robert Jenssen
A measure of uncertainty in the relevance scores is computed by taking the standard deviation across the relevance scores produced by each model in the ensemble, which in turn is used to make the explanations more reliable.
no code implementations • 3 Sep 2020 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance.
2 code implementations • 21 Apr 2020 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation.
1 code implementation • 15 Apr 2020 • Luigi T. Luppino, Mads A. Hansen, Michael Kampffmeyer, Filippo M. Bianchi, Gabriele Moser, Robert Jenssen, Stian N. Anfinsen
We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces and reduce the impact of change pixels on the learning objective.
1 code implementation • 15 Mar 2020 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs.
1 code implementation • 9 Mar 2020 • Qinghui Liu, Michael Kampffmeyer, Robert Jessen, Arnt-Børre Salberg
In this article, we propose a novel architecture called the dense dilated convolutions' merging network (DDCM-Net) to address this task.
2 code implementations • 20 Jan 2020 • Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer
In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives.
3 code implementations • 13 Jan 2020 • Luigi Tommaso Luppino, Michael Kampffmeyer, Filippo Maria Bianchi, Gabriele Moser, Sebastiano Bruno Serpico, Robert Jenssen, Stian Normann Anfinsen
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection.
no code implementations • 25 Sep 2019 • Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen
In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.
no code implementations • 25 Sep 2019 • Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen
In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.
no code implementations • 7 Sep 2019 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task.
1 code implementation • 30 Aug 2019 • Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
We propose a network for semantic mapping called the Dense Dilated Convolutions Merging Network (DDCM-Net) to provide a deep learning approach that can recognize multi-scale and complex shaped objects with similar color and textures, such as buildings, surfaces/roads, and trees in very high resolution remote sensing images.
1 code implementation • 12 Apr 2019 • Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen
Reject inference is the process of attempting to infer the creditworthiness status of the rejected applications.
no code implementations • 14 Mar 2019 • Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen
We show that it is possible to steer the latent representations in the latent space of the VAE using the Weight of Evidence and forming a specific grouping of the data that reflects the customers' creditworthiness.
no code implementations • 13 Feb 2019 • Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Lorenzo Livi, Arnt-Børre Salberg, Robert Jenssen
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function.
no code implementations • 29 Nov 2018 • Daniel J. Trosten, Andreas S. Strauman, Michael Kampffmeyer, Robert Jenssen
The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths.
no code implementations • 29 Jul 2018 • Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Zeya Wang, Wei Dai, Eric P. Xing
Motivated by the zoom-in operation of a pathologist using a digital microscope, RAZN learns a policy network to decide whether zooming is required in a given region of interest.
no code implementations • 19 Jul 2018 • Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Robert Jenssen, Lorenzo Livi
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network.
no code implementations • 17 Jul 2018 • Yu-jia Zhang, Michael Kampffmeyer, Xiaodan Liang, Min Tan, Eric P. Xing
Video summarization plays an important role in video understanding by selecting key frames/shots.
no code implementations • 10 Jul 2018 • Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann, Eric Xing
Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models.
no code implementations • 10 Jul 2018 • Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Zeya Wang, Wei Dai, Eric P. Xing
Specifically, we propose a model that enforces our intuition that prediction masks should be domain independent.
no code implementations • 7 Jun 2018 • Rogelio Andrade Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen
We use the VAE and show that transforming the input data into a meaningful representation, it is possible to steer configurations in the latent space of the VAE.
3 code implementations • CVPR 2019 • Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yu-jia Zhang, Eric P. Xing
Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.
no code implementations • 9 May 2018 • Filippo Maria Bianchi, Lorenzo Livi, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen
In this work, we propose a novel autoencoder architecture based on recurrent neural networks to generate compressed representations of MTS.
no code implementations • 30 Apr 2018 • Yu-jia Zhang, Michael Kampffmeyer, Xiaodan Liang, Dingwen Zhang, Min Tan, Eric P. Xing
Specifically, DTR-GAN learns a dilated temporal relational generator and a discriminator with three-player loss in an adversarial manner.
no code implementations • 20 Apr 2018 • Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yu-jia Zhang, Eric P. Xing
We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task.
no code implementations • 17 Nov 2017 • Andreas Storvik Strauman, Filippo Maria Bianchi, Karl Øyvind Mikalsen, Michael Kampffmeyer, Cristina Soguero-Ruiz, Robert Jenssen
Clinical measurements that can be represented as time series constitute an important fraction of the electronic health records and are often both uncertain and incomplete.
no code implementations • 21 Sep 2017 • Michael Kampffmeyer, Arnt-Børre Salberg, Robert Jenssen
Techniques to improve urban land cover classification performance in remote sensing include fusion of data from different sensors with different data modalities.
no code implementations • 8 Feb 2017 • Michael Kampffmeyer, Sigurd Løkse, Filippo Maria Bianchi, Robert Jenssen, Lorenzo Livi
In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space.
no code implementations • 18 Jan 2017 • Filippo Maria Bianchi, Michael Kampffmeyer, Enrico Maiorino, Robert Jenssen
In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics.