Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Locality Constrained Deep Supervised Hashing for Image Retrieval
Authors: Hao Zhu, Shenghua Gao
IJCAI 2017 | Venue PDF | 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 EMAIL, EMAIL, |
| 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. |