Locality Constrained Deep Supervised Hashing for Image Retrieval

Authors: Hao Zhu, Shenghua Gao

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on the CIFAR-10 and NUS-WIDE datasets show that our method significantly boosts the accuracy of image retrieval... 4 Experiments We compare our model with several baselines on two widely used benchmark datasets: CIFAR-10 [Krizhevsky and Hinton, 2009] and NUS-WIDE [Chua et al., 2009].
Researcher Affiliation Collaboration Hao Zhu1, Shenghua Gao2 3M Cogent Beijing1 School of Information Science and Technology, Shanghai Tech University2 allenhaozhu@gmail.com, gaoshh@shanghaitech.edu.cn,
Pseudocode No The paper describes methods and equations but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper mentions comparing with other methods 'by using the codes provided by authors' for those methods, but it does not state that its own code is open-source or provide a link.
Open Datasets Yes We compare our model with several baselines on two widely used benchmark datasets: CIFAR-10 [Krizhevsky and Hinton, 2009] and NUS-WIDE [Chua et al., 2009].
Dataset Splits No The paper specifies training and query (test) sets for CIFAR-10 and NUS-WIDE, but does not explicitly provide details for a separate validation split.
Hardware Specification Yes the model of GPU used in our experiments is GTX980-Ti which only has 6GB memory. ... It is worth noting that our CNN-F model can process more than 1200 images per second for feature extraction by using a GTX980-Ti GPU.
Software Dependencies No The paper mentions 'Our method is implemented with Mat Conv Net [Vedaldi and Lenc, 2015]' but does not provide a specific version number for the software.
Experiment Setup No The paper describes model architecture details and mentions convergence iterations but does not explicitly state concrete hyperparameter values such as learning rate, batch size, or optimizer settings.