Related papers: Progressive Modality Cooperation for Multi-Modalit…
Existing domain adaptation methods on visual sentiment classification typically are investigated under the single-source scenario, where the knowledge learned from a source domain of sufficient labeled data is transferred to the target…
Adversarial adaptation models have demonstrated significant progress towards transferring knowledge from a labeled source dataset to an unlabeled target dataset. Partial domain adaptation (PDA) investigates the scenarios in which the source…
Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domain, making most…
RGB-Infrared (RGB-IR) multimodal perception is fundamental to embodied multimedia systems operating in complex physical environments. Although recent cross-modal fusion methods have advanced RGB-IR detection, the optimization dynamics…
Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain. However, in many applications, relevant labeled source datasets may not be available, and…
Recently, generative domain adaptation has achieved remarkable progress, enabling us to adapt a pre-trained generator to a new target domain. However, existing methods simply adapt the generator to a single target domain and are limited to…
Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to…
Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play a core contribution to their success. However, in unsupervised domain adaptation scenarios, we…
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for…
Learning based on multimodal data has attracted increasing interest recently. While a variety of sensory modalities can be collected for training, not all of them are always available in development scenarios, which raises the challenge to…
Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…
Existing methods of cross-modal domain adaptation for 3D semantic segmentation predict results only via 2D-3D complementarity that is obtained by cross-modal feature matching. However, as lacking supervision in the target domain, the…
Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of…
Practical real world datasets with plentiful categories introduce new challenges for unsupervised domain adaptation like small inter-class discriminability, that existing approaches relying on domain invariance alone cannot handle…
We present a novel multiple-source unsupervised model for text classification under domain shift. Our model exploits the update rates in document representations to dynamically integrate domain encoders. It also employs a probabilistic…
Unsupervised domain adaptation aims to leverage labeled data from a source domain to learn a classifier for an unlabeled target domain. Among its many variants, open set domain adaptation (OSDA) is perhaps the most challenging, as it…
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…
Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one source domain to another…
Multi-Source Domain Adaptation (MSDA) aims to mitigate changes in data distribution when transferring knowledge from multiple labeled source domains to an unlabeled target domain. However, existing MSDA techniques assume target domain…