arXiv research

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…

End-to-end PGL framework tackles open-set domain shift.

Paper tackles open set domain adaptation by detecting unknown classes.

In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and n…

A new method trains deep neural networks for open set domain adaptation without negative open set difference.

Optimal transport method rejects new classes and adjusts class ratios for open set domain adaptation.

New method reduces label and data shifts between domains using optimal transport.

A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whether the target contains a single homogeneous domain or multiple heterogeneous domains, existing wor…

SKADA-bench evaluates unsupervised DA methods across diverse modalities.

Paper develops new algorithms for unsupervised multi-class domain adaptation.

New framework tackles multi-source domain adaptation with optimism and consistency.

DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.

Study on MHD equilibria on curved spaces without symmetries.

This work evaluates PDA methods without target labels, revealing significant accuracy drops.

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, …

In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand, we propose an improvement of the previous approach proposed by Germain et al. (2…

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample, then there will be differences between how the training data is distributed and…

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 …

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Gr…

Nowadays, users open multiple accounts on social media platforms and e-commerce sites, expressing their personal preferences on different domains. However, users' behaviors change across domains, depending on the content that users interact with, such as movies, music, clothing and retail products. In this paper, we pr…

In domain adaptation, classifiers with information from a source domain adapt to generalize to a target domain. However, an adaptive classifier can perform worse than a non-adaptive classifier due to invalid assumptions, increased sensitivity to estimation errors or model misspecification. Our goal is to develop a doma…

NMIXX fine-tunes embeddings for finance, outperforming general models in Korean.

Paper introduces new PAC-Bayesian bounds for multi-view domain adaptation.

The paper improves generalization bounds for domain adaptation.

Edge devices adapt pre-trained models to local data without backpropagation.

SCTL scales causal domain adaptation without prior knowledge.

Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the …

Proxy methods adapt to distribution shifts without explicitly modeling latent confounders.

In this paper we prove that, given an open Riemann surface $M$ and an integer $n\ge 3$, the set of complete conformal minimal immersions $M\to\mathbb{R}^n$ with $\overline{X(M)}=\mathbb{R}^n$ forms a dense subset in the space of all conformal minimal immersions $M\to\mathbb{R}^n$ endowed with the compact-open topology.…

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

This thesis studies domain adaptation under minimal distribution similarity assumptions using moments.

Study of SU(2,1) character varieties on one-holed torus.

Learn to automatically plug domain-specific modules into a common network.

Unified analysis of generalization and sample complexity for semi-supervised domain adaptation.

High fidelity behavior prediction of intelligent agents is critical in many applications. However, the prediction model trained on the training set may not generalize to the testing set due to domain shift and time variance. The challenge motivates the adoption of online adaptation algorithms to update prediction model…

Improves ASR accuracy for domain mismatch using machine translation.

New bounds on inscribed triangles in arbitrary planar domains.

Paper develops a model for verifying facts in tables without pre-retrieved evidence.

Open set recognition problems exist in many domains. For example in security, new malware classes emerge regularly; therefore malware classification systems need to identify instances from unknown classes in addition to discriminating between known classes. In this paper we present a neural network based representation…

TransCal calibrates DA models with lower bias and variance.

Adapting the method of Andrews-Clutterbuck we prove an eigenvalue gap theorem for a class of non symmetric second order linear elliptic operators on a convex domain in euclidean space. The class of operators includes the Bakry-Emery laplacian with potential and any operator with second order term the laplacian whose fi…

In Domain Adaptation (DA), the category-relevant losses usually occupy a dominant position, while they are usually built with hard or soft labels in existing models. We observed that hard labels are overconfident due to hard samples existed, and soft labels are ambiguous as too many small noisy probabilities involved, …

Proposes a label propagation framework for domain adaptation.

Paper proposes a method to adapt classifiers using complementary labels instead of true labels.

Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance. However, even these methods do not focus on a key aspect: maintaining performance on…

Algorithm adapts to shifting domains with minimal label queries.

DRDA robustly adapts models across domains with mismatched distributions.

Study reveals adversarially robust domain adaptation is harder to generalize across domains.