Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation

Authors: Qiuyan He, Minghua Deng

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on benchmarks show the state-of-the-art performance of GSS compared to typical methods, including source models or source data dependent methods.
Researcher Affiliation Academia Qiuyan He1, Minghua Deng1,2,3*, 1School of Mathematical Sciences, Peking University 2Center for Statistical Science, Peking University 3Center for Quantitative Biology, Peking University EMAIL, EMAIL
Pseudocode No The paper describes methods and formulas but does not include a dedicated pseudocode or algorithm block.
Open Source Code No The paper does not provide a direct link to a source code repository or an explicit statement about the release of their implementation code for GSS.
Open Datasets Yes We use four benchmark datasets in DA: Office (Saenko et al. 2010), Office Home (OH) (Venkateswara et al. 2017), Vis DA (Peng et al. 2017) and Domain Net (Peng et al. 2019).
Dataset Splits Yes We follow existing methods (Saito and Saenko 2021; Deng et al. 2021) to split datasets and the split |Ls Lt|/|Ls Lt|/|Lt Ls| is showed in each table. Type Method Office (10/10/11) Vis DA (6/3/3) A2W D2W W2D A2D D2A W2A Avg
Hardware Specification No The paper does not specify the exact hardware components (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No The paper mentions using Res Net50 (He et al. 2016) pre-trained on Image Net (Deng et al. 2009) as the backbone network, but does not provide specific version numbers for software libraries, frameworks, or programming languages used for implementation.
Experiment Setup Yes For Office, Office Home, Vis DA and Domain Net, we set Kclu = 35, 70, 20 and 300 respectively under all DA settings. Besides, we let e0 = 0.1 in all experiments.