paper-with-me

홈 › Papers

Domain Generalization via Multidomain Discriminant Analysis

2019-07-25 · Shoubo Hu, Kun Zhang, Zhitang Chen, Laiwan Chan

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data may rarely be identical to those of the source data. In this paper, we propose Multidomain Discriminant Analysis (MDA) to address DG of classification tasks in general situations. MDA learns a domain-invariant feature transformation that aims to achieve appealing properties, including a minimal divergence among domains within each class, a maximal separability among classes, and overall maximal compactness of all classes. Furthermore, we provide the bounds on excess risk and generalization error by learning theory analysis. Comprehensive experiments on synthetic and real benchmark datasets demonstrate the effectiveness of MDA.

📄 PDF Abstract BibTeX arXiv:1907.11216

Code (0)

등록된 구현이 없습니다.

Tasks

Domain GeneralizationLearning Theory

Similar Papers 제목 키워드 기반

Modular Domain Adaptation for Conformer-Based Streaming ASR

2023-05-22 · Qiujia Li, Bo Li, Dongseong Hwang, Tara N. Sainath 외

Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech recognition on a mixture of data from al…

Domain Adaptationspeech-recognitionSpeech Recognition

BERTCaps: BERT Capsule for Persian Multi-Domain Sentiment Analysis

2024-12-07 · Mohammadali Memari, Soghra Mikaeyl Nejad, Amir Parsa Rabiei, Mehrshad Eisaei 외

Multidomain sentiment analysis involves estimating the polarity of an unstructured text by exploiting domain specific information. One of the main issues common to the approaches discussed in the literature is their poor…

Binary ClassificationClassificationdomain classificationSentiment Analysis+1

Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting

2024-02-06 · Mingyue Guo, Binghui Chen, Zhaoyi Yan, YaoWei Wang 외

Multidomain crowd counting aims to learn a general model for multiple diverse datasets. However, deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. …

Crowd Counting

Conformational ensembles of intrinsically disordered proteins and flexible multidomain proteins

2021-12-10 · F. Emil Thomasen, Kresten Lindorff-Larsen

Intrinsically disordered proteins (IDPs) and multidomain proteins with flexible linkers show a high level of structural heterogeneity and are best described by ensembles consisting of multiple conformations with associat…

Multidomain Multimodal Fusion For Human Action Recognition Using Inertial Sensors

2020-08-22 · Zeeshan Ahmad, Naimul Khan

One of the major reasons for misclassification of multiplex actions during action recognition is the unavailability of complementary features that provide the semantic information about the actions. In different domains …

Action RecognitionTemporal Action Localization