IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

Authors: Haixin Wang, Hao Wu, Jinan Sun, Shikun Zhang, Chong Chen, Xian-Sheng Hua, Xiao Luo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments conducted on benchmark datasets confirm the superior performance of our proposed IDEA compared to a variety of competitive baselines.
Researcher Affiliation Collaboration 1Peking University, 2University of Science and Technology of China, 3Terminus Group, 4University of California, Los Angeles
Pseudocode Yes Algorithm 1 Training Algorithm of IDEA
Open Source Code No The paper does not include a statement about releasing source code or a link to a code repository.
Open Datasets Yes Experiments are conducted on different benchmark datasets: (1) Office-Home dataset [57]: ... (2) Office-31 dataset [42]: ... (3) Digits dataset: We focus on MNIST [26] and USPS [23]...
Dataset Splits No The paper specifies a 'training set' and 'test queries' but does not explicitly mention a separate 'validation' set or its split.
Hardware Specification Yes We perform experiments on an A100-40GB GPU.
Software Dependencies No The paper mentions 'mini-batch SGD with momentum' for optimization but does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The batch size is set to 36 and the learning rate is fixed as 0.001.