Zobrazeno 1 - 10
of 3 027
pro vyhledávání: '"Peng, Xi"'
Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outliers (e.g., data from the web or other datasets) in training. However,
Externí odkaz:
http://arxiv.org/abs/2411.14049
A major obstacle to the advancements of machine learning models in marine science, particularly in sonar imagery analysis, is the scarcity of AI-ready datasets. While there have been efforts to make AI-ready sonar image dataset publicly available, th
Externí odkaz:
http://arxiv.org/abs/2411.00172
Large pretrained foundation models demonstrate exceptional performance and, in some high-stakes applications, even surpass human experts. However, most of these models are currently evaluated primarily on prediction accuracy, overlooking the validity
Externí odkaz:
http://arxiv.org/abs/2411.00132
The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due to the co
Externí odkaz:
http://arxiv.org/abs/2410.15624
Data stream clustering reveals patterns within continuously arriving, potentially unbounded data sequences. Numerous data stream algorithms have been proposed to cluster data streams. The existing data stream clustering algorithms still face signific
Externí odkaz:
http://arxiv.org/abs/2409.04698
Large pre-trained Vision-Language Models (VLMs) have become ubiquitous foundational components of other models and downstream tasks. Although powerful, our empirical results reveal that such models might not be able to identify fine-grained concepts.
Externí odkaz:
http://arxiv.org/abs/2407.14412
We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1) Mismatch b
Externí odkaz:
http://arxiv.org/abs/2407.12240
Federated Learning is widely employed to tackle distributed sensitive data. Existing methods primarily focus on addressing in-federation data heterogeneity. However, we observed that they suffer from significant performance degradation when applied t
Externí odkaz:
http://arxiv.org/abs/2407.04949
Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors
Externí odkaz:
http://arxiv.org/abs/2406.19602
Autor:
Zhang, Qingyang, Wei, Yake, Han, Zongbo, Fu, Huazhu, Peng, Xi, Deng, Cheng, Hu, Qinghua, Xu, Cai, Wen, Jie, Hu, Di, Zhang, Changqing
Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of scenarios, including autonomous driving and medical diagnosis. However,
Externí odkaz:
http://arxiv.org/abs/2404.18947