Qu, S., Zou, T., Roehrbein, F., Lu, C., Chen, G., Tao, D., & Jiang, C. (2023).Upcycling models under domain and category shift. InProceedings of CVPR. Quinonero-Candela, J., Sugiyama, M., Schwaighofer, A., & Lawrence, N. D. (2008).Dataset shift in machine learning. ...
& Cui, P. A theoretical analysis on independence-driven importance weighting for covariate-shift generalization. In International Conference on Machine Learning 24803–24829 (PMLR, 2022). Kuang, K., Cui, P., Athey, S., Xiong, R. & Li, B. Stable prediction across unknown environments. In ...
However, during the 1950s and 1960s a progressive northern shift in wintering distribution occurred as numbers of geese wintering in Louisiana and Arkansas... - 《Wildlife Monographs》 被引量: 158发表: 2004年 Genetic diversity and population structure in cultivated sunflower and a comparison to ...
When machine learning models are deployed on a test distribution different from the training distribution, they can perform poorly, but overestimate their performance. In this work, we aim to better estimate a model's performance under distribution shift, without supervision. To do so, we use a ...
musical_distribution_shift数据集由约翰内斯·开普勒大学林茨计算感知研究所与LIT AI实验室创建,旨在评估自动音乐转录系统在不同音乐分布偏移下的性能。数据集包括MIDI文件和真实钢琴录音,分为不同音乐流派和随机组合的子集,以测试系统的泛化能力。数据集的创建过程包括MIDI文件的收集、合成及在统一声学条件下的录制。该数...
Anomaly Detection under Distribution Shift Tri Cao, Jiawen Zhu, and Guansong Pang* School of Computing and Information Systems, Singapore Management University Abstract Anomaly detection (AD) is a crucial machine learn- ing task that aims to learn patterns from a set of normal training samples to...
robustnessadversarial-attacksdata-centricgraph-neural-networksout-of-distributiondistribution-shifttest-time-adaptation UpdatedJun 23, 2023 Python Distilling Large Vision-Language Model with Out-of-Distribution Generalizability (ICCV 2023) machine-learningdeep-learningzero-shot-learningfew-shot-learningout-of-di...
/Visual-AI/Dissect-OOD-OSRKeywords: Out-of-Distribution Detection, Open-set Recognition1 IntroductionAny practical machine learning model is likely toencounter test-time samples which dif f er substan-tially from its training set; i.e., models are likelyto encounter test-time distribution shift....
This repo provides the scripts for generating the proposed MetaShift, which offers a resource of 1000s of distribution shifts. Abstract Understanding the performance of machine learning model across diverse data distributions is critically important for reliable applications. Motivated by this, there is ...
Unsupervised self-organised mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys We present an application of unsupervised machine learning the self-organized map (SOM) as a tool for visualizing, exploring and mining the catalogues of... JE...