Incremental Unsupervised Domain-Adversarial Training of Neural Networks

  title={Incremental Unsupervised Domain-Adversarial Training of Neural Networks},
  author={Antonio Javier Gallego and Jorge Calvo-Zaragoza and Robert B. Fisher},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as domain adaptation (DA). Deep neural networks… 

Incremental Unsupervised Domain Adaptation Through Optimal Transport

The proposed approach, called DA-OTP, aims to learn a gradual subspace alignment of the source and target domains through Supervised Locality Preserving Projection, so that projected data in the joint low-dimensional latent subspace can be domain-invariant and easily separable.

Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign

Noise augmentation (NoiseAug) is provided which is a non-trivial byproduct of simplifying GradAlign and achieves SOTA results in FGSM AT, and it is verified that this is caused not by data augmentation effect (inject noise on image) but by improved local linearity.

Dual Adversarial Attention Mechanism for Unsupervised Domain Adaptive Medical Image Segmentation

A dual-attention domain-adaptative segmentation network (DADASeg-Net) for cross-modality medical image segmentation, which regularizes the domain adaptation module with two attention maps respectively from the space and class perspectives.

Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information

A robust multi-source co-adaptation framework by mining diverse correlation information (MACI) among domains and features with l2,1−norm as well as correlation metric regularization is proposed, which can make MACI use relevant knowledge from multiple sources by exploiting the developed correlation metric function.

Multi-Hierarchical Fusion to Capture the Latent Invariance for Calibration-Free Brain-Computer Interfaces

A deep learning decoding method based on multi-hierarchical representation fusion (MHRF) on MI-EEG can serve as a robust and competitive method to improve inter-session and inter-subject transferability, adding anticipation and prospective thoughts to the practical implementation of a calibration-free BCI system.

Importance of Features Selection, Attributes Selection, Challenges and Future Directions for Medical Imaging Data: A Review

This review is meant to describe feature selection techniques in a medical domain with their pros and cons and to signify its application in imaging data and data mining algorithms, and provides the importance of feature selection for correct classification of medical infections.

Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition

A robust Latent Multi-source Adaptation (LMA) framework for cross-subject/dataset emotion recognition with EEG signals by uncovering multiple domain-invariant latent subspaces by jointly aligning the statistical and semantic distribution discrepancies between each source and target pair.

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

This overview examines the field from multiple aspects, including regulations across the world and relevant current technologies, and introduces an example computer vision-based UAV flight safety pipeline, taking into account all issues present in current autonomous drones.



A DIRT-T Approach to Unsupervised Domain Adaptation

Two novel and related models are proposed: the Virtual Adversarial Domain Adaptation (VADA) model, which combines domain adversarial training with a penalty term that punishes the violation the cluster assumption, and the Decision-boundary Iterative Refinement Training with a Teacher (DIRT-T) models, which takes the VADA model as initialization and employs natural gradient steps to further minimize the Cluster assumption violation.

Asymmetric Tri-training for Unsupervised Domain Adaptation

This work proposes the use of an asymmetric tri-training method for unsupervised domain adaptation, where two networks are used to label unlabeled target samples, and one network is trained by the pseudo-labeled samples to obtain target-discriminative representations.

Adversarial Discriminative Domain Adaptation

It is shown that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and the promise of the approach is demonstrated by exceeding state-of-the-art unsupervised adaptation results on standard domain adaptation tasks as well as a difficult cross-modality object classification task.

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

A novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant low-dimensional structures across domains to correct data distribution mismatch and leverages available unlabeled target examples to exploit the underlying intrinsic information in the target domain.

Semi-supervised Domain Adaptation on Manifolds

This work considers an explicit form of transformation functions and especially linear transformations that maps examples from the source to the target domain, and argues that by proper preprocessing of the data from both source and target domains, the feasible transformation functions can be characterized by a set of rotation matrices.

Semi-Supervised Domain Adaptation via Minimax Entropy

A novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model for semi-supervised domain adaptation (SSDA) setting, setting a new state of the art for SSDA.

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

This generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain, and outperforms the state-of-the-art on a number of unsupervised domain adaptation scenarios by large margins.

Associative Domain Adaptation

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the

Generate to Adapt: Aligning Domains Using Generative Adversarial Networks

This work proposes an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space by inducing a symbiotic relationship between the learned embedding and a generative adversarial network.

A theory of learning from different domains

A classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains and shows how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class.