A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.
UDA learns target domain from unlabeled data via source knowledge transfer.
A novel unsupervised domain adaptation method using hierarchical optimal transport.
Method generates intermediate domains to align source and target domains.
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we…
Method maps imperfect simulations to observed stellar spectra using unsupervised domain adaptation.
SKADA-bench evaluates unsupervised DA methods across diverse modalities.
Prototype extraction framework for domain adaptation.
Improves model calibration and selection in unsupervised domain adaptation.
Two new methods improve graph embedding without needing a complete graph structure.
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local feature…
Geometric approach for unsupervised word embedding alignment.
Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.
Paper presents a Transformer model for automatic domain adaptation.
The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples, the standard approach is to learn a common representation for both source and t…
Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in practice: 1) only limited labeled samples are available due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noises (e.g., mi…
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of discrepancies between the two distributions. Most existing algorithms can only handle uns…
Proposes TFDF to learn transferable and discriminative features for unsupervised domain adaptation.
Framework for domain adaptation using pseudo-labels from unlabeled data.
Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the classifier in the target domain are two widely used objectives. Existing methods often …
Algorithm adapts pretrained semantic segmentation models to new domains.
Benchmark for UDA in time series classification.
Calibrates network confidence for unsupervised domain adaptation.
New method removes pseudo-label bias for unsupervised domain adaptation.
We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a tw…
Paper proposes a method to adapt classifiers using complementary labels instead of true labels.
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised …
Unsupervised domain adaptation improves with privileged information.
Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher layers in the model, the representations become more task-specific and less generalizable. Recent resear…
Stein discrepancy improves UDA performance in low-data scenarios.
PAS method improves UDA by progressively refining subspaces for reliable pseudo-labels.
Unsupervised domain adaptation (UDA) aims at inferring class labels for unlabeled target domain given a related labeled source dataset. Intuitively, a model trained on source domain normally produces higher uncertainties for unseen data. In this work, we build on this assumption and propose to adapt from source to targ…
Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation deals with the challenge of adapting a model trained from a data-rich source domai…
Method aggregates models with different hyper-parameters to adapt to target domain.
Contradistinguisher learns to distinguish target domain without aligning source and target domains.
LOBSTUR-GNN adapts bootstrapping for unsupervised GNNs, improving node representation learning.
Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset. We propose to improve the discriminative ability of the target domain representation by simultaneously learning tightly clustered target …
Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. A pr…
In this paper, we propose a simple model referred as Contradistinguisher (CTDR) for unsupervised domain adaptation whose objective is to jointly learn to contradistinguish on unlabeled target domain in a fully unsupervised manner along with prior knowledge acquired by supervised learning on an entirely different domain…
SAHMM-VAE separates sources adaptively using hidden Markov priors.
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain feat…
New framework tackles multi-source domain adaptation with optimism and consistency.
State-of-the-art speaker recognition relays on models that need a large amount of training data. This models are successful in tasks like NIST SRE because there is sufficient data available. However, in real applications, we usually do not have so much data and, in many cases, the speaker labels are unknown. We present…
This paper proposes a method to compress and adapt CNNs for real-world applications.
Proposes a framework to improve domain adaptation without labeled data.
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as wel…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of lab…
Clarinet uses complementary labels to train classifiers with less source data.