LIVIVO - Search results -

Search results

Result 1 - 10 of total 22

Search options

Article ; Online: A Two-Stream Continual Learning System With Variational Domain-Agnostic Feature Replay.

Lao, Qicheng / Jiang, Xiang / Havaei, Mohammad / Bengio, Yoshua

IEEE transactions on neural networks and learning systems

2022 Volume 33, Issue 9, Page(s) 4466–4478

Abstract: Learning in nonstationary environments is one of the biggest challenges in machine learning. Nonstationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., ... ...

Abstract	Learning in nonstationary environments is one of the biggest challenges in machine learning. Nonstationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This article aims to tackle this challenge with a modularized two-stream continual learning (CL) system, where the model is required to learn new tasks from a support stream and adapted to new domains in the query stream while maintaining previously learned knowledge. To deal with both drifts within and across the two streams, we propose a variational domain-agnostic feature replay-based approach that decouples the system into three modules: an inference module that filters the input data from the two streams into domain-agnostic representations, a generative module that facilitates the high-level knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We demonstrate the effectiveness of our proposed approach in addressing the two fundamental scenarios and complex scenarios in two-stream CL.
Language	English
Publishing date	2022-08-31
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2021.3057453
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Stain transfer using Generative Adversarial Networks and disentangled features.

Moghadam, Atefeh Ziaei / Azarnoush, Hamed / Seyyedsalehi, Seyyed Ali / Havaei, Mohammad

Computers in biology and medicine

2022 Volume 142, Page(s) 105219

Abstract: With the digitization of histopathology, machine learning algorithms have been developed to help pathologists. Color variation in histopathology images degrades the performance of these algorithms. Many models have been proposed to resolve the impact of ... ...

Abstract	With the digitization of histopathology, machine learning algorithms have been developed to help pathologists. Color variation in histopathology images degrades the performance of these algorithms. Many models have been proposed to resolve the impact of color variation and transfer histopathology images to a single stain style. Major shortcomings include manual feature extraction, bias on a reference image, being limited to one style to one style transfer, dependence on style labels for source and target domains, and information loss. We propose two models, considering these shortcomings. Our main novelty is using Generative Adversarial Networks (GANs) along with feature disentanglement. The models extract color-related and structural features with neural networks; thus, features are not hand-crafted. Extracting features helps our models do many-to-one stain transformations and require only target-style labels. Our models also do not require a reference image by exploiting GAN. Our first model has one network per stain style transformation, while the second model uses only one network for many-to-many stain style transformations. We compare our models with six state-of-the-art models on the Mitosis-Atypia Dataset. Both proposed models achieved good results, but our second model outperforms other models based on the Histogram Intersection Score (HIS). Our proposed models were applied to three datasets to test their performance. The efficacy of our models was also evaluated on a classification task. Our second model obtained the best results in all the experiments with HIS of 0.88, 0.85, 0.75 for L-channel, a-channel, and b-channel, using the Mitosis-Atypia Dataset and accuracy of 90.3% for classification.
MeSH term(s)	Algorithms ; Coloring Agents ; Image Processing, Computer-Assisted/methods ; Machine Learning ; Neural Networks, Computer
Chemical Substances	Coloring Agents
Language	English
Publishing date	2022-01-05
Publishing country	United States
Document type	Journal Article
ZDB-ID	127557-4
ISSN	1879-0534 ; 0010-4825
ISSN (online)	1879-0534
ISSN	0010-4825
DOI	10.1016/j.compbiomed.2022.105219
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 653: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Article ; Online: Conditional generation of medical images via disentangled adversarial inference.

Havaei, Mohammad / Mao, Ximeng / Wang, Yiping / Lao, Qicheng

Medical image analysis

2021 Volume 72, Page(s) 102106

Abstract: Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) ... ...

Abstract	Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) use a conditioning factor to generate images and have shown great success in recent years. Intuitively, the information in an image can be divided into two parts: 1) content which is presented through the conditioning vector and 2) style which is the undiscovered information missing from the conditioning vector. Current practices in using cGANs for medical image generation, only use a single variable for image generation (i.e., content) and therefore, do not provide much flexibility nor control over the generated image. In this work we propose DRAI-a dual adversarial inference framework with augmented disentanglement constraints-to learn from the image itself, disentangled representations of style and content, and use this information to impose control over the generation process. In this framework, style is learned in a fully unsupervised manner, while content is learned through both supervised learning (using the conditioning vector) and unsupervised learning (with the inference mechanism). We undergo two novel regularization steps to ensure content-style disentanglement. First, we minimize the shared information between content and style by introducing a novel application of the gradient reverse layer (GRL); second, we introduce a self-supervised regularization method to further separate information in the content and style variables. For evaluation, we consider two types of baselines: single latent variable models that infer a single variable, and double latent variable models that infer two variables (style and content). We conduct extensive qualitative and quantitative assessments on two publicly available medical imaging datasets (LIDC and HAM10000) and test for conditional image generation, image retrieval and style-content disentanglement. We show that in general, two latent variable models achieve better performance and give more control over the generated image. We also show that our proposed model (DRAI) achieves the best disentanglement score and has the best overall performance.
MeSH term(s)	Humans ; Image Processing, Computer-Assisted ; Machine Learning
Language	English
Publishing date	2021-05-24
Publishing country	Netherlands
Document type	Journal Article
ZDB-ID	1356436-5
ISSN	1361-8423 ; 1361-8431 ; 1361-8415
ISSN (online)	1361-8423 ; 1361-8431
ISSN	1361-8415
DOI	10.1016/j.media.2021.102106
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 5206: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Book ; Online: Pitfalls of Conditional Batch Normalization for Contextual Multi-Modal Learning

Sheth, Ivaxi / Rahman, Aamer Abdul / Havaei, Mohammad / Kahou, Samira Ebrahimi

2022

Abstract: Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance on a single modality, neural networks cannot reach human level accuracy with respect to multiple modalities. This ... ...

Abstract	Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance on a single modality, neural networks cannot reach human level accuracy with respect to multiple modalities. This is a particularly challenging task due to variations in the structure of respective modalities. Conditional Batch Normalization (CBN) is a popular method that was proposed to learn contextual features to aid deep learning tasks. This technique uses auxiliary data to improve representational power by learning affine transformations for convolutional neural networks. Despite the boost in performance observed by using CBN layers, our work reveals that the visual features learned by introducing auxiliary data via CBN deteriorates. We perform comprehensive experiments to evaluate the brittleness of CBN networks to various datasets, suggesting that learning from visual features alone could often be superior for generalization. We evaluate CBN models on natural images for bird classification and histology images for cancer type classification. We observe that the CBN network learns close to no visual features on the bird classification dataset and partial visual features on the histology dataset. Our extensive experiments reveal that CBN may encourage shortcut learning between the auxiliary data and labels. Comment: Accepted at ICBINB workshop @ NeurIPS 2022
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	006 ; 004
Publishing date	2022-11-28
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: FL Games

Gupta, Sharut / Ahuja, Kartik / Havaei, Mohammad / Chatterjee, Niladri / Bengio, Yoshua

A Federated Learning Framework for Distribution Shifts

2022

Abstract: Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. However, participating clients typically each hold data from a different distribution, which can yield to catastrophic ... ...

Abstract	Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. However, participating clients typically each hold data from a different distribution, which can yield to catastrophic generalization on data from a different client, which represents a new domain. In this work, we argue that in order to generalize better across non-i.i.d. clients, it is imperative to only learn correlations that are stable and invariant across domains. We propose FL GAMES, a game-theoretic framework for federated learning that learns causal features that are invariant across clients. While training to achieve the Nash equilibrium, the traditional best response strategy suffers from high-frequency oscillations. We demonstrate that FL GAMES effectively resolves this challenge and exhibits smooth performance curves. Further, FL GAMES scales well in the number of clients, requires significantly fewer communication rounds, and is agnostic to device heterogeneity. Through empirical evaluation, we demonstrate that FL GAMES achieves high out-of-distribution performance on various benchmarks. Comment: Accepted as ORAL at NeurIPS Workshop on Federated Learning: Recent Advances and New Challenges. arXiv admin note: text overlap with arXiv:2205.11101
Keywords	Computer Science - Machine Learning
Publishing date	2022-10-31
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: CT-SGAN

Pesaranghader, Ahmad / Wang, Yiping / Havaei, Mohammad

Computed Tomography Synthesis GAN

2021

Abstract: Diversity in data is critical for the successful training of deep learning models. Leveraged by a recurrent generative adversarial network, we propose the CT-SGAN model that generates large-scale 3D synthetic CT-scan volumes ($\geq 224\times224\times224$) ...

Abstract	Diversity in data is critical for the successful training of deep learning models. Leveraged by a recurrent generative adversarial network, we propose the CT-SGAN model that generates large-scale 3D synthetic CT-scan volumes ($\geq 224\times224\times224$) when trained on a small dataset of chest CT-scans. CT-SGAN offers an attractive solution to two major challenges facing machine learning in medical imaging: a small number of given i.i.d. training data, and the restrictions around the sharing of patient data preventing to rapidly obtain larger and more diverse datasets. We evaluate the fidelity of the generated images qualitatively and quantitatively using various metrics including Fr\'echet Inception Distance and Inception Score. We further show that CT-SGAN can significantly improve lung nodule detection accuracy by pre-training a classifier on a vast amount of synthetic data. Comment: In Proceedings of MICCAI Deep Generative Models workshop, October 2021
Keywords	Electrical Engineering and Systems Science - Image and Video Processing ; Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2021-10-14
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: FL Games

Gupta, Sharut / Ahuja, Kartik / Havaei, Mohammad / Chatterjee, Niladri / Bengio, Yoshua

A federated learning framework for distribution shifts

2022

Abstract	Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. However, participating clients typically each hold data from a different distribution, whereby predictive models with strong in-distribution generalization can fail catastrophically on unseen domains. In this work, we argue that in order to generalize better across non-i.i.d. clients, it is imperative to only learn correlations that are stable and invariant across domains. We propose FL Games, a game-theoretic framework for federated learning for learning causal features that are invariant across clients. While training to achieve the Nash equilibrium, the traditional best response strategy suffers from high-frequency oscillations. We demonstrate that FL Games effectively resolves this challenge and exhibits smooth performance curves. Further, FL Games scales well in the number of clients, requires significantly fewer communication rounds, and is agnostic to device heterogeneity. Through empirical evaluation, we demonstrate that FL Games achieves high out-of-distribution performance on various benchmarks.
Keywords	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
Publishing date	2022-05-23
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

Jiang, Xiang / Lao, Qicheng / Matwin, Stan / Havaei, Mohammad

2020

Abstract: We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment perspective. Current ... ...

Abstract	We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment perspective. Current methods for class-conditioned domain alignment aim to explicitly minimize a loss function based on pseudo-label estimations of the target domain. However, these methods suffer from pseudo-label bias in the form of error accumulation. We propose a method that removes the need for explicit optimization of model parameters from pseudo-labels directly. Instead, we present a sampling-based implicit alignment approach, where the sample selection procedure is implicitly guided by the pseudo-labels. Theoretical analysis reveals the existence of a domain-discriminator shortcut in misaligned classes, which is addressed by the proposed implicit alignment approach to facilitate domain-adversarial learning. Empirical results and ablation studies confirm the effectiveness of the proposed approach, especially in the presence of within-domain class imbalance and between-domain class distribution shift. Comment: Accepted at ICML2020. For code, see https://github.com/xiangdal/implicit_alignment
Keywords	Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition ; Statistics - Machine Learning ; 68T07
Subject code	004
Publishing date	2020-06-08
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Conditional Generation of Medical Images via Disentangled Adversarial Inference

Havaei, Mohammad / Mao, Ximeng / Wang, Yiping / Lao, Qicheng

2020

Abstract	Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) use a conditioning factor to generate images and have shown great success in recent years. Intuitively, the information in an image can be divided into two parts: 1) content which is presented through the conditioning vector and 2) style which is the undiscovered information missing from the conditioning vector. Current practices in using cGANs for medical image generation, only use a single variable for image generation (i.e., content) and therefore, do not provide much flexibility nor control over the generated image. In this work we propose a methodology to learn from the image itself, disentangled representations of style and content, and use this information to impose control over the generation process. In this framework, style is learned in a fully unsupervised manner, while content is learned through both supervised learning (using the conditioning vector) and unsupervised learning (with the inference mechanism). We undergo two novel regularization steps to ensure content-style disentanglement. First, we minimize the shared information between content and style by introducing a novel application of the gradient reverse layer (GRL); second, we introduce a self-supervised regularization method to further separate information in the content and style variables. We show that in general, two latent variable models achieve better performance and give more control over the generated image. We also show that our proposed model (DRAI) achieves the best disentanglement score and has the best overall performance. Comment: Published in Medical Image Analysis
Keywords	Electrical Engineering and Systems Science - Image and Video Processing ; Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2020-12-08
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

Lao, Qicheng / Jiang, Xiang / Havaei, Mohammad / Bengio, Yoshua

2020

Abstract: Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., ... ...

Abstract	Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining previously learned knowledge. To deal with both drifts, we propose variational domain-agnostic feature replay, an approach that is composed of three components: an inference module that filters the input data into domain-agnostic representations, a generative module that facilitates knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We address the two fundamental scenarios in continuous domain adaptation, demonstrating the effectiveness of our proposed approach for practical usage.
Keywords	Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition ; Statistics - Machine Learning
Subject code	006
Publishing date	2020-03-09
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED