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
A review of single-source deep unsupervised visual domain adaptation
Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
Generalizing to unseen domains: A survey on domain generalization
Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …
the same. To this end, a key requirement is to develop models that can generalize to unseen …
Fishr: Invariant gradient variances for out-of-distribution generalization
Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …
for real-world applications. To this end, there has been a growing surge of interest to learn …
A fine-grained analysis on distribution shift
Robustness to distribution shifts is critical for deploying machine learning models in the real
world. Despite this necessity, there has been little work in defining the underlying …
world. Despite this necessity, there has been little work in defining the underlying …
Self-supervised augmentation consistency for adapting semantic segmentation
We propose an approach to domain adaptation for semantic segmentation that is both
practical and highly accurate. In contrast to previous work, we abandon the use of …
practical and highly accurate. In contrast to previous work, we abandon the use of …
Invariant risk minimization
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant
correlations across multiple training distributions. To achieve this goal, IRM learns a data …
correlations across multiple training distributions. To achieve this goal, IRM learns a data …
Learning robust global representations by penalizing local predictive power
Despite their renowned in-domain predictive power, convolutional neural networks are
known to rely more on high-frequency patterns that humans deem superficial than on low …
known to rely more on high-frequency patterns that humans deem superficial than on low …
The risks of invariant risk minimization
Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution
generalization which assumes that some aspects of the data distribution vary across the …
generalization which assumes that some aspects of the data distribution vary across the …
Cycle self-training for domain adaptation
Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant
representations to narrow the domain shift, which are empirically effective but theoretically …
representations to narrow the domain shift, which are empirically effective but theoretically …
Domain generalization using causal matching
In the domain generalization literature, a common objective is to learn representations
independent of the domain after conditioning on the class label. We show that this objective …
independent of the domain after conditioning on the class label. We show that this objective …