RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation

Authors: Qucheng Peng, Zhengming Ding, Lingjuan Lyu, Lichao Sun, Chen Chen

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our method achieves state-of-the-art performance on several cross-domain benchmarks under both singleand multi-source blackbox domain adaptation.
Researcher Affiliation Collaboration 1Center for Research in Computer Vision, University of Central Florida 2Department of Computer Science, Tulane University 3Sony AI 4Lehigh University qucheng.peng@knights.ucf.edu, chen.chen@crcv.ucf.edu
Pseudocode No The paper describes methods using equations and figures, but no explicitly labeled 'Pseudocode' or 'Algorithm' block is present.
Open Source Code No The paper does not contain any explicit statements about releasing source code or provide a link to a code repository.
Open Datasets Yes Datasets. We use four popular benchmark datasets for evaluation. Office-31 [Saenko et al., 2010]... Image-CLEF [Long et al., 2017]... Office-Home [Venkateswara et al., 2017]... Vis DA-C [Peng et al., 2017]
Dataset Splits No The paper mentions training epochs and learning rates but does not explicitly provide the train/validation/test dataset splits (e.g., percentages or specific sample counts) or references specific predefined splits with citations for all datasets used.
Hardware Specification Yes Training is conducted on an NVIDIA RTX A5000 GPU.
Software Dependencies No Py Torch [Paszke et al., 2019] is used for the implementation.
Experiment Setup Yes We set the batch size to 64 and adopt SGD [Ruder, 2016] as the optimizer, with a momentum of 0.9 and a weight decay of 1e-3. For Office-31 and Office Home, the learning rate is set as 1e-3 for the convolutional layers and 1e-2 for the rest. For Vis DA-C, we choose 1e-4 for the convolutional layers and 1e-3 for the rest...Label smoothing [Muller et al., 2019] is used on the leverage of source client, with 100 epochs for all the tasks. For the training procedure on target client, we train 30 epochs for all the tasks...For the hyper-parameters in Eq. 11, we set β = 1.2, γ = 0.6, and θ = 0.3. ...the subnetwork width is set as 0.84 .