Generalized Unprovoked Vulvodynia

Arbel, Ariel; Lev‐Sagie, Ahinoam

doi:10.1002/9781119482598.ch42

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EBMs capture the dependencies between variables by imposing a rangeconstrained energy on each configuration of the variables, which has been implemented extensively in the field of generative modeling [15][16][17]. In [18], the authors theoretically demonstrate that OOD data can easily lead to over-prediction by softmax classifiers.…”

Section: Energy-based Models (Ebms)mentioning

confidence: 99%

Open set domain adaptive method based on energy separation strategy

Chai

Wang

Long

et al. 2023

Preprint

View full text Add to dashboard Cite

Open Set Domain Adaptation (OSDA) aims to reduce the variation across domains while distinguishing between known samples and unknown samples. However, existing OSDA methods are based on deep neural network classifiers to separate unknown samples, which leads the network to produce overconfident predictions and fails to establish the boundary between the known and the unknown. We propose an Energy-based Open Set Domain Adaptation method (EOS). Specifically, EOS is a new two-stage approach of separation followed by alignment. We use an energy-based anomaly detection strategy as a separation method for unknown samples, transforming the traditional K-way classification task into a K+1-dimensional classifier that uses an additional dimension to model the uncertainty of Out-of-distribution (OOD) samples. Then, we use a coarse-to-fine separation method to continuously adjust the separation results and add the exact separation results as weights in the alignment process, weighing their importance to the feature distribution alignment. In the alignment phase we also optimize our separation network module at the same time, so that the module can be better adapted with invariant features. We have done experiments on the standard ground Office-31, Office-Home, and VisDA-2017 benchmarks, and the results show that our approach outperforms our competitors in most cases.

show abstract

Section: Energy-based Models (Ebms)mentioning

confidence: 99%