Domain Generalization through the Lens of Angular Invariance

Authors: Yujie Jin, Xu Chu, Yasha Wang, Wenwu Zhu

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on multiple DG benchmark datasets validate the effectiveness of the proposed AIDGN method.
Researcher Affiliation Academia 1 Peking University, Beijing, China 2 Tsinghua University, Beijing, China
Pseudocode No The paper describes its methodology through mathematical derivations and textual explanations but does not include any explicit pseudocode or algorithm blocks.
Open Source Code Yes Codes are avalable at https://github.com/Jin Yujie99/aidgn
Open Datasets Yes We conduct our experiments on four public benchmark datasets to evaluate the effectiveness of the proposed AIDGN. PACS [Li et al., 2017], VLCS [Fang et al., 2013], Office Home [Venkateswara et al., 2017], Terra Incognita [Beery et al., 2018]
Dataset Splits Yes For training, we randomly split each training domain into 8:2 training/validation splits, choose the model on the overall validation set, and then evaluate its performance on the target domain set.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions using the Adam optimizer and the Domain Bed framework but does not provide specific version numbers for programming languages, libraries, or other software dependencies.
Experiment Setup Yes We construct a mini-batch containing all source domains where each domain has 32 images. We freeze all the batch normalization (BN) layers from pre-trained Res Net since different domains in a mini-batch follow different distributions. The network is trained for 5000 iterations using the Adam [Kingma and Ba, 2015] optimizer. To estimate δy,ϕ and µd,y,ϕ in AIDGN loss (16), we treat all δy,ϕ as one single hyperparameter δ, and perform in-batch estimation for the d-th domain norm scale parameter, i.e., µd, while ignoring the index y and ϕ.