Exploring Safety Supervision for Continual Test-time Domain Adaptation
Authors: Xu Yang, Yanan Gu, Kun Wei, Cheng Deng
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results demonstrate that our method achieves state-of-the-art performance on several benchmark datasets. 4 Experiments In this section, we review the proposed method on several benchmark tasks: CIFAR10-to-CIFAR10C (Standard and Gradual), CIFAR100-to-CIFAR100C, and Image Netto-Image Net-C. |
| Researcher Affiliation | Academia | Xu Yang , Yanan Gu , Kun Wei and Cheng Deng Xidian University {xuyang.xd, yanangu.xd, weikunsk, chdeng.xd}@gmail.com |
| Pseudocode | No | The paper describes the proposed methods using textual descriptions and mathematical equations, but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code or provide links to a code repository for the described methodology. |
| Open Datasets | Yes | We use CIFAR10, CIFAR100, and Image Net as the source domain datasets, and CIFAR10C, CIFAR100C, and Image Net-C as the corresponding target domain datasets, respectively. The target domain datasets were originally created to evaluate the robustness of classification networks [Hendrycks and Dietterich, 2019]. |
| Dataset Splits | No | The paper describes source data (training) and continually changing target test data (for adaptation and evaluation), but it does not specify a distinct validation dataset split with proportions or sample counts needed for hyperparameter tuning or early stopping. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU or CPU models, memory specifications, or types of computing clusters used for running experiments. |
| Software Dependencies | No | The paper mentions software like 'Adam' for optimization and specific network architectures (Wide Res Net28, Res Ne Xt-29, Res Net-50), but does not provide specific version numbers for any software dependencies, libraries, or frameworks. |
| Experiment Setup | Yes | We use Adam to optimize the network and set the learning rate to 1e-3. The data augmentation strategy is the same as [Wang et al., 2022], including color jitter, gaussian blur, gaussian noise, random affine, and random horizontal flip, N = 8. [...] N = 4. [...] The smoothing factor α is set as 0.99. |