Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
Open-world machine learning: A review and new outlooks
Machine learning has achieved remarkable success in many applications. However,
existing studies are largely based on the closed-world assumption, which assumes that the …
existing studies are largely based on the closed-world assumption, which assumes that the …
SURE: SUrvey REcipes for building reliable and robust deep networks
In this paper we revisit techniques for uncertainty estimation within deep neural networks
and consolidate a suite of techniques to enhance their reliability. Our investigation reveals …
and consolidate a suite of techniques to enhance their reliability. Our investigation reveals …
Gradient-regularized out-of-distribution detection
One of the challenges for neural networks in real-life applications is the overconfident errors
these models make when the data is not from the original training distribution. Addressing …
these models make when the data is not from the original training distribution. Addressing …
Out-of-distribution detection in long-tailed recognition with calibrated outlier class learning
Existing out-of-distribution (OOD) methods have shown great success on balanced datasets
but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples …
but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples …
Towards trustworthy dataset distillation
Efficiency and trustworthiness are two eternal pursuits when applying deep learning in
practical scenarios. Considering efficiency, dataset distillation (DD) endeavors to reduce …
practical scenarios. Considering efficiency, dataset distillation (DD) endeavors to reduce …
Online safety analysis for llms: a benchmark, an assessment, and a path forward
While Large Language Models (LLMs) have seen widespread applications across
numerous fields, their limited interpretability poses concerns regarding their safe operations …
numerous fields, their limited interpretability poses concerns regarding their safe operations …
Revisiting confidence estimation: Towards reliable failure prediction
Reliable confidence estimation is a challenging yet fundamental requirement in many risk-
sensitive applications. However, modern deep neural networks are often overconfident for …
sensitive applications. However, modern deep neural networks are often overconfident for …
Test optimization in dnn testing: A survey
This article presents a comprehensive survey on test optimization in deep neural network
(DNN) testing. Here, test optimization refers to testing with low data labeling effort. We …
(DNN) testing. Here, test optimization refers to testing with low data labeling effort. We …
Rcl: Reliable continual learning for unified failure detection
Deep neural networks are known to be overconfident for what they don't know in the wild
which is undesirable for decision-making in high-stakes applications. Despite quantities of …
which is undesirable for decision-making in high-stakes applications. Despite quantities of …
Unified classification and rejection: A one-versus-all framework
Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-
of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural …
of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural …