Cycle Self-Refinement for Multi-Source Domain Adaptation

Authors: Chaoyang Zhou, Zengmao Wang, Bo Du, Yong Luo

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on Office-31, Office-Home and Domain Net show that the proposed method outperforms the state-of-the-art methods for most tasks.
Researcher Affiliation Academia 1 School of Computer Science, Wuhan University 2 National Engineering Research Center for Multimedia Software, Wuhan University 3 Institute of Artificial Intelligence, Wuhan University 4 Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University 5 Hubei Luojia Laboratory, China zhoucy,wangzengmao,dubo,luoyong@whu.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Code is released at https://github.com/zcy866/CSR.
Open Datasets Yes Three popular benchmark datasets are adopted in the experiments, i.e. Office-31 (Saenko et al. 2010), Office-Home (Venkateswara et al. 2017) and Domain Net (Peng et al. 2019).
Dataset Splits No The paper states how domains are used for source and target roles, but does not explicitly provide percentages or counts for training, validation, or test splits within the datasets.
Hardware Specification Yes Experiments are done on Nvidia V100.
Software Dependencies No The paper mentions Resnet-50 and Resnet-101, and Rand Augment, but does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes Meanwhile, for trade-off parameters β and filtering threshold τ, we set (0.7, 0.9) for Office31 and Office-home, and (0.7, 0.6) for Domain Net. The Rand Augment(Cubuk et al. 2020) is adopted as data augmentation for T. We utilize the same learning rate and schedule as (Zhu, Zhuang, and Wang 2019).