Adversarial Domain Adaptation with Domain Mixup

Authors: Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang6502-6509

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments prove that the proposed approach can achieve superior performance on tasks with various degrees of domain shift and data complexity. Experiments In this section, we first introduce the experimental setup. Then, the classification performance on three domain adaptation benchmarks are presented. Finally, ablation study and sensitivity analysis are conducted for the proposed approach.
Researcher Affiliation Collaboration 1Shanghai Jiao Tong University, China, 2Huawei Hisilicon, 3Anhui University, 4Youtu Lab, Tencent, 5Huawei Noah s Ark Lab
Pseudocode Yes Algorithm 1 Training procedure of DM-ADA
Open Source Code No The paper does not contain any explicit statement about releasing the source code for their method or a link to a code repository.
Open Datasets Yes In this set of experiments, three digits datasets are used: MNIST (L ecun et al. 1998), USPS (Hull 1994) and Street View House Numbers (SVHN) (Netzer et al. 2011). and Office-31 (Saenko et al. 2010) is a standard domain adaptation benchmark commonly used in previous researches. and The Vis DA-2017 (Peng et al. 2017) challenge proposes a large-scale dataset for visual domain adaptation.
Dataset Splits No The paper mentions using 'training set' and evaluating on 'validation set' (for VisDA-2017 challenge), but does not provide specific details on how they split their data (e.g., percentages or sample counts for training, validation, and test sets) for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions 'Py Torch deep learning framework' but does not specify its version or any other software dependencies with version numbers.
Experiment Setup Yes In this part of experiments, we construct four subnetworks with train-from-scratch architectures following (Sankaranarayanan et al. 2018). Four Adam optimizers with base learning rate 0.0004 are utilized to optimize these submodels for 100 epochs. The hyper-parameters ω and ϕ are set as 0.1 and 0.01 respectively, and their values are constant in all experiments. All of the input images of encoder and discriminator are resized to 32 32.