Moderately Distributional Exploration for Domain Generalization
Authors: Rui Dai, Yonggang Zhang, Zhen Fang, Bo Han, Xinmei Tian
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results show that MODE achieves competitive performance compared to state-of-the-art baselines. ... In this section, we demonstrate the superiority of our approach on several DG benchmarks. ... We show the Leave-one-domain-out classification accuracies on Digit-DG in Table 2. It can be observed that our approach achieves the highest accuracy in most domains and the second-highest accuracy in the remaining domain. |
| Researcher Affiliation | Academia | 1University of Science and Technology of China, Hefei, China 2Department of Computer Science, Hong Kong Baptist University, Hong Kong, China 3Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, Australia 4Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China. |
| Pseudocode | Yes | Algorithm 1 MODE ... Algorithm 2 Fourier-based MODE ... Algorithm 3 Ada IN-based MODE |
| Open Source Code | Yes | 1Code: github.com/Rxsw/MODE. |
| Open Datasets | Yes | We evaluate our approach on three standard DG benchmark datasets described below. More results include VLCS (Torralba & Efros, 2011), Domain Net (Peng et al., 2019) and Mini-Domain Net (Zhou et al., 2021a) are given in the Appendix D. Digits-DG (Zhou et al., 2020a) consists of 4 digit datasets: MNIST (M) (Le Cun et al., 1998), MNIST-M (M-M) (Ganin & Lempitsky, 2015), SVHN (SV) (Netzer et al., 2011) and SYN (SY) (Ganin & Lempitsky, 2015)... PACS (Li et al., 2017)... Office-Home (Venkateswara et al., 2017)... |
| Dataset Splits | Yes | For Digits-DG... 80% of the selected images are used for training, and 20% are used for validation. ... For PACS and Office-Home... use the training-validation-test split provided by (Li et al., 2017). ... For a fair comparison, we use the training-validation-test split same as Xiao et al. (2021). |
| Hardware Specification | No | The paper does not explicitly state the specific hardware used for experiments, such as GPU models, CPU types, or memory specifications. It focuses on software and training parameters. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries (e.g., 'PyTorch 1.9', 'Python 3.8'). It only mentions general tools like 'SGD optimizer'. |
| Experiment Setup | Yes | For Digits-DG, we use the backbone introduced by (Zhou et al., 2020b; Xu et al., 2021). All images are resized to 32 × 32. Following Xu et al. (2021), we train the network using an SGD optimizer with a learning rate of 0.05, batch size of 128, a momentum of 0.9, and weight decay 5e-4 for 50 epochs. The learning rate is decayed by 0.1 every 20 epochs. We use random cropping in data augmentation. For PACS and Office-Home, following Li et al. (2017); Xu et al. (2021), we use a pre-trained ResNet-18 backbone (He et al., 2016), all images are resized to 224 × 224. We train the network using SGD optimizer with learning rate 5e-4, momentum 0.9, and weight decay 5e-4. We train the model for 80 epochs with batch size 16 and 50 epochs with batch size 32, respectively. The learning rate is decayed by 0.1 every 40 epochs. We use the standard augmentation protocol in Li et al. (2017); Xu et al. (2021). The hyperparameters of our approach: The number of inner steps K, inner step size µ, β, γ, and The number of style providers M. The settings of these hyperparameters are shown in Appendix D.4 (Table 13 and Table 14). |