reproducibilityindex.ai

Feature Learning Based Deep Supervised Hashing with Pairwise Labels

Authors: Wu-Jun Li, Sheng Wang, Wang-Cheng Kang

Reproducibility Variable	Result	LLM Response
Research Type	Experimental	Experiments on real datasets show that our DPSH method can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.
Researcher Affiliation	Academia	Wu-Jun Li, Sheng Wang and Wang-Cheng Kang National Key Laboratory for Novel Software Technology Department of Computer Science and Technology, Nanjing University, China
Pseudocode	Yes	Algorithm 1 Learning algorithm for DPSH.
Open Source Code	No	The paper does not include any explicit statement or link indicating that the source code for the methodology described is publicly available.
Open Datasets	Yes	We compare our model with several baselines on two widely used benchmark datasets: CIFAR-10 and NUS-WIDE.
Dataset Splits	Yes	The hyper-parameter in DPSH is chosen by a validation set, which is 10 for CIFAR-10 and 100 for NUS-WIDE unless otherwise stated.
Hardware Specification	Yes	All our experiments for DPSH are completed with Mat Conv Net [Vedaldi and Lenc, 2015] on a NVIDIA K80 GPU server.
Software Dependencies	No	The paper mentions 'Mat Conv Net' as the framework used but does not provide a specific version number for it or any other software dependencies.
Experiment Setup	Yes	The hyper-parameter in DPSH is chosen by a validation set, which is 10 for CIFAR-10 and 100 for NUS-WIDE unless otherwise stated.