Optimal Projection Guided Transfer Hashing for Image Retrieval

Authors: Ji Liu, Lei Zhang8754-8761

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various benchmark databases verify that our method outperforms many state-of-the-art learning to hash methods. The implementation details are available at https://github.com/liuji93/GTH.
Researcher Affiliation Academia Ji Liu, Lei Zhang School of Microelectronics and Communication Engineering, Chongqing University, China jiliu@cqu.edu.cn, leizhang@cqu.edu.cn
Pseudocode Yes Algorithm 1 Optimal Projection Guided Transfer Hashing
Open Source Code Yes The implementation details are available at https://github.com/liuji93/GTH.
Open Datasets Yes We perform the experiments on three groups benchmark datasets: PIE-C29&PIE-C05 from PIE (Sim, Baker, and Bsat 2002), Amazon&Dslr from Office (Saenko et al. 2010), and VOC2007&Caltech101 from VLCS (Torralba and Efros 2011).
Dataset Splits No The paper specifies training and testing sets, but does not explicitly mention a separate validation set or its size/percentage for model selection.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers.
Experiment Setup Yes For our GTH, we empirically set λ1 to 0.1 and λ2 to 1. The code length is set to 32. ... where τ denotes the step size. We empirically set τ = 0.1.