A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection

Authors: Wenhao Wang, Yifan Sun, Yi Yang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that ASL outperforms state-of-the-art methods by a clear margin, confirming that solving the symmetric-asymmetric conflict is critical for ICD.
Researcher Affiliation Collaboration Wenhao Wang1,2*, Yifan Sun2, Yi Yang3 1 Re LER, University of Technology Sydney 2 Baidu Research 3 Zhejiang University wangwenhao0716@gmail.com, sunyifan01@baidu.com, yangyics@zju.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes The NDEC dataset and code are available at https://github.com/Wang Wenhao0716/ASL.
Open Datasets Yes Based on existing ICD datasets, this paper constructs a new dataset by additionally adding 100, 000 and 24, 252 hard negative pairs into the training and test set, respectively. The NDEC dataset and code are available at https://github.com/Wang Wenhao0716/ASL.
Dataset Splits No The paper mentions 'training' and 'test' sets with specific image counts but does not provide details about a distinct 'validation' dataset split or how it was derived.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper mentions various deep learning techniques and losses (e.g., Cos Face, triplet loss) but does not provide specific software dependencies with version numbers (e.g., PyTorch 1.9, Python 3.8).
Experiment Setup No The paper mentions replacing 8192-dim features with 2048-dim features and using Cos Face as a loss function, but it does not provide specific hyperparameters such as learning rate, batch size, or optimizer settings for the experimental setup.