Related papers: SODA: Robust Training of Test-Time Data Adaptors
The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…
Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse…
Semi-supervised domain adaptation (SSDA) presents a critical hurdle in computer vision, especially given the frequent scarcity of labeled data in real-world settings. This scarcity often causes foundation models, trained on extensive…
3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…
Changes in the data distribution at test time can have deleterious effects on the performance of predictive models $p(y|x)$. We consider situations where there are additional meta-data labels (such as group labels), denoted by $z$, that can…
A domain (distribution) shift between training and test data often hinders the real-world performance of deep neural networks, necessitating unsupervised domain adaptation (UDA) to bridge this gap. Online source-free UDA has emerged as a…
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…
Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled target images leveraging source labeled ones. In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the…
Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but also domain…
Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…
Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration…
In recent years, researchers have been paying increasing attention to the threats brought by deep learning models to data security and privacy, especially in the field of domain adaptation. Existing unsupervised domain adaptation (UDA)…
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and…
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled…
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. The conventional DA strategy is to align the feature distributions of the two domains. Recently, increasing…
Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused…
Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that…
Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually…