Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization
Authors: Houcheng Su, Weihao Luo, Daixian Liu, Mengzhu Wang, Jing Tang, Junyang Chen, Cong Wang, Zhenghan Chen
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we investigate the effectiveness of our proposed improvements on three state-of-the-art methods, to demonstrate the validity of our approach. Comparative experiments are conducted across four datasets: PACS (Li et al. 2017), Office Home (Venkateswara et al. 2017), Digit DG (Zhou et al. 2020), and Domain Net (Peng et al. 2019). In addition, we perform ablation studies to facilitate a thorough discourse on our methodology. |
| Researcher Affiliation | Academia | Houcheng Su1*, Weihao Luo2*, Daixian Liu 3, Mengzhu Wang4 , Jing Tang4, Junyang Chen5, Cong Wang6, Zhenghan Chen7 1University of Macau 2Donghua University 3Sichuan Agricultural University 4Hebei University of Technology 5Shenzhen University 6The Hong Kong Polytechnic University 7Peking University |
| Pseudocode | No | The paper describes methods and formulations but does not include any clearly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | Code: https://github.com/bamboosir920/SAMALTDG. |
| Open Datasets | Yes | Comparative experiments are conducted across four datasets: PACS (Li et al. 2017), Office Home (Venkateswara et al. 2017), Digit DG (Zhou et al. 2020), and Domain Net (Peng et al. 2019). |
| Dataset Splits | Yes | PACS: We randomly split each domain into 90% for training and 10% for validation. ... Office Home: Following (Carlucci et al. 2019), we randomly split each domain into 90% for training and 10% for validation. ... Digits DG: We use the original train validation split in (Zhou et al. 2020) with 600 images per class per dataset. We randomly split each domain into 90% for training and 10% for validation. ... Domain Net: For data sets, we adopted the default partitioning method of data sets, with 80% as the training set and 20% as the validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like 'SGD optimizer' and 'Res Net18 and Res Net50' but does not specify their version numbers or any other software dependencies with specific versions. |
| Experiment Setup | Yes | For all experiments, we employed the SGD optimizer with a momentum and decay rate set at 0.9 and 0.0005, respectively. The learning rate was kept at 0.001. For our proposed enhancements, which we denote as SAM, the base optimizer was set to SGD, with rho at 0.1, learning rate at 0.01, adaptive set to False, weight decay at 0.0005, momentum at 0.9, and nesterov enabled. Concurrently, the weight of Maximum Square Loss was represented by γ and set as 1 in the comparison experiment. |