Hamming Compatible Quantization for Hashing

Authors: Zhe Wang, Ling-Yu Duan, Jie Lin, Xiaofang Wang, Tiejun Huang, Wen Gao

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiment results have shown our approach significantly improves the performance of various stateof-the-art hashing methods while maintaining fast retrieval speed.
Researcher Affiliation Academia Zhe Wang, Ling-Yu Duan, Jie Lin, Xiaofang Wang, Tiejun Huang, Wen Gao The Institute of Digital Media, Peking University, Beijing, China {zhew, lingyu, jielin, xiaofangwang, tjhuang, wgao}@pku.edu.cn
Pseudocode Yes Algorithm 1 shows the pseudo-code.
Open Source Code No The paper does not contain an explicit statement about releasing its source code or a link to a code repository.
Open Datasets Yes Extensive experiments were carried out over three widely used retrieval benchmark datasets, Label Me22K [Torralba et al., 2008], CIFAR-10 [Krizhevsky, 2009] and NUSWIDE [Chua et al., 2009].
Dataset Splits No The paper mentions using a random selection of 1000 images for queries and the remaining for the database, and selecting 1000 images for training the quantization boundaries. It discusses parameter tuning using λ, which implies a validation process, but does not explicitly provide percentages or counts for training/validation/test splits, nor does it refer to standard validation splits for the entire dataset used for training their model (only for the quantization boundaries).
Hardware Specification Yes We measure the search time on an Intel(R) Core(TM) i5 3470 CPU at 3.20GHz with a single thread.
Software Dependencies No The paper does not specify software dependencies with version numbers.
Experiment Setup Yes In the following experiments, we set λ = 0.6, 0.7, 0.8, 0.9 at code size 32, 64, 128, 256, respectively.