Zobrazeno 1 - 10
of 40 358
pro vyhledávání: '"Free model"'
Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder for white-
Externí odkaz:
http://arxiv.org/abs/2409.10643
The abundance and blue color of super-early (redshift $z>10$), luminous galaxies discovered by JWST can be explained if radiation-driven outflows have ejected their dust on kpc-scales. To test this hypothesis, we predict the ALMA detectability of suc
Externí odkaz:
http://arxiv.org/abs/2409.17223
We propose the $\textit{lifted linear model}$, and derive model-free prediction intervals that become tighter as the correlation between predictions and observations increases. These intervals motivate the $\textit{Lifted Coefficient of Determination
Externí odkaz:
http://arxiv.org/abs/2410.08958
In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images from all t
Externí odkaz:
http://arxiv.org/abs/2407.13771
Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existing works have verified and improved its effectiveness in several aspec
Externí odkaz:
http://arxiv.org/abs/2405.09863
Autor:
Huang, Yichen, Kochmar, Ekaterina
Text simplification lacks a universal standard of quality, and annotated reference simplifications are scarce and costly. We propose to alleviate such limitations by introducing REFeREE, a reference-free model-based metric with a 3-stage curriculum.
Externí odkaz:
http://arxiv.org/abs/2403.17640
Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This interface boos
Externí odkaz:
http://arxiv.org/abs/2404.00108
Autor:
Peng, Boyang, Qu, Sanqing, Wu, Yong, Zou, Tianpei, He, Lianghua, Knoll, Alois, Chen, Guang, jiang, changjun
Deep learning has achieved remarkable progress in various applications, heightening the importance of safeguarding the intellectual property (IP) of well-trained models. It entails not only authorizing usage but also ensuring the deployment of models
Externí odkaz:
http://arxiv.org/abs/2403.04149
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Tang, Chen, Meng, Yuan, Jiang, Jiacheng, Xie, Shuzhao, Lu, Rongwei, Ma, Xinzhu, Wang, Zhi, Zhu, Wenwu
Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability.
Externí odkaz:
http://arxiv.org/abs/2401.01543