Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval

Authors: Xu Wang, Dezhong Peng, Ming Yan, Peng Hu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To verify the effectiveness of the proposed method, extensive experiments are conducted on four benchmark datasets compared with six state-of-the-art methods.
Researcher Affiliation Collaboration Xu Wang1, Dezhong Peng1,3,4, Ming Yan2, Peng Hu1* 1College of Computer Science, Sichuan University, Chengdu, China 2Centre for Frontier AI Research (CFAR), A*STAR, Singapore 3Sichuan Zhiqian Technology Co., Ltd, Chengdu, China 4Chengdu Ruibei Yingte Information Technology Ltd. Company, Chengdu, China
Pseudocode Yes Algorithm 1 briefly summarizes the optimization procedure of the proposed Co DA approach.
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets Yes To verify the effectiveness of the proposed method, we conduct extensive experiments on four benchmark datasets, i.e., Office31 (Saenko et al. 2010), Image-CLEF (Long et al. 2017), Office Home (Venkateswara et al. 2017), and Adaptiope (Ringwald and Stiefelhagen 2021).
Dataset Splits No For each dataset, we randomly partition the data into training and test sets, with an 80-20 ratio for each category. No explicit mention of a separate validation set.
Hardware Specification Yes The proposed approach is implemented by Py Torch with two Nvidia Ge Force RTX 2080 GPUs.
Software Dependencies No The paper mentions "implemented by Py Torch" but does not specify a version number for PyTorch or other software dependencies.
Experiment Setup Yes For a fair comparison, the hyper-parameters are set as η = 0.95 nb = 16, λ = 0.01, Ne = 20, τ = 0.01, and α = 0.003 for all datasets.