Joint weight optimization for partial domain adaptation via kernel statistical distance estimation
S Chen - Neural Networks, 2024 - Elsevier
Abstract The goal of Partial Domain Adaptation (PDA) is to transfer a neural network from a
source domain (joint source distribution) to a distinct target domain (joint target distribution) …
source domain (joint source distribution) to a distinct target domain (joint target distribution) …
RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
N Du, C Tang, Y Jiang, Y Meng, Z Wang - arXiv preprint arXiv:2408.05752, 2024 - arxiv.org
Performing unsupervised domain adaptation on resource-constrained edge devices is
challenging. Existing research typically adopts architecture optimization (eg, designing …
challenging. Existing research typically adopts architecture optimization (eg, designing …
Latency Adjustable Transformer Encoder for Language Understanding
S Kachuee, M Sharifkhani - arXiv preprint arXiv:2201.03327, 2022 - arxiv.org
Adjusting the latency, power, and accuracy of natural language understanding models is a
desirable objective of an efficient architecture. This paper proposes an efficient Transformer …
desirable objective of an efficient architecture. This paper proposes an efficient Transformer …
[图书][B] Transfer Learning Based on Gaussian Process and Generative Adversarial Network
K Yang - 2022 - search.proquest.com
Traditional machine learning techniques can only achieve better results when the training
data source domain and the test data target domain have the same functional probability …
data source domain and the test data target domain have the same functional probability …