Natural Supervised Hashing
Authors: Qi Liu, Hongtao Lu
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our experiment, training 16-bit and 96-bit code on NUS-WIDE cost respectively only 3 and 6 minutes. ... We evaluate our method on 4 datasets: NUS-WIDE IAPRTC122, ESPGAME 3, MIRFLICKR25K 4. For NUSWIDE [Chua et al., 2009], we use the 500 dimensional bagof-words vectors provided by the authors. For the other three, we use the 512 dimensional GIST features provided by [Guillaumin et al., 2010]. Each dataset is split into a database and a query set. Statistics of datasets are given in table 1. |
| Researcher Affiliation | Academia | Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering, Shanghai Jiao Tong University, P.R. China luoguliu@gmail.com, lu-ht@cs.sjtu.edu.cn |
| Pseudocode | No | No pseudocode or algorithm blocks were explicitly labeled or provided in a structured format within the paper. |
| Open Source Code | No | The paper does not provide any links to open-source code or explicitly state that the code for their methodology is available. |
| Open Datasets | Yes | We evaluate our method on 4 datasets: NUS-WIDE IAPRTC122, ESPGAME 3, MIRFLICKR25K 4. For NUSWIDE [Chua et al., 2009], we use the 500 dimensional bagof-words vectors provided by the authors. For the other three, we use the 512 dimensional GIST features provided by [Guillaumin et al., 2010]. ... 2http://www.imageclef.org/photodata 3http://www.hunch.net/ jl/ 4http://press.liacs.nl/mirflickr/ |
| Dataset Splits | No | The paper mentions splitting data into 'database' and 'query' sets for evaluation and samples 5000 points from databases for training some methods. However, it does not explicitly specify a distinct 'validation' set or its size/split for hyperparameter tuning or early stopping, only 'training' and 'query' (testing) sets. |
| Hardware Specification | Yes | All our results are obtained on a laptop with Intel Core i5-3210M 2.50 GHz and 12 GB RAM. |
| Software Dependencies | No | The paper mentions using "Pegasos [Shalev-Shwartz et al., 2011] as our SVM" but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | Yes | In experiments, we give NSH 50 training iterations and set λ = 10 4 for all cases. ... The kernel we choose is RBF (x, y) = exp(||x y||/σ2) , where σ is set to an appropriate value. 1000 anchors are sampled from databases for all datasets except MIRFLICKR25K, for which we use only 500 anchors considering it is not large-scale and contains less labels. |