Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

Authors: Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results and ablation studies confirm the effectiveness of the proposed approach, especially in the presence of within-domain class imbalance and between-domain class distribution shift. and 4. Experiments Datasets. We evaluate on Office-31, Office-Home and Vis DA2017.
Researcher Affiliation Collaboration 1Imagia, Canada 2Dalhousie University, Canada 3Mila, Universit e de Montr eal, Canada 4Polish Academy of Sciences, Poland.
Pseudocode Yes Algorithm 1 The proposed implicit alignment training
Open Source Code Yes Code: https://github.com/xiangdal/implicit_alignment
Open Datasets Yes Datasets. We evaluate on Office-31 (Saenko et al., 2010), Office-Home (Venkateswara et al., 2017) and Vis DA2017 (synthetic real) (Peng et al., 2017)
Dataset Splits No The paper uses well-known datasets but does not explicitly provide specific training, validation, or test dataset split percentages or counts for its experiments.
Hardware Specification Yes Xiang Jiang acknowledges the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.
Software Dependencies No The paper mentions deep learning models and datasets but does not provide specific version numbers for software dependencies like PyTorch, TensorFlow, or CUDA.
Experiment Setup Yes The batch size is 31 for Office-31 and 50 for Office-Home. and We only update pseudo-labels periodically, i.e., every 20 steps, instead of at every training step.