Complementary Binary Quantization for Joint Multiple Indexing

Authors: Qiang Fu, Xu Han, Xianglong Liu, Jingkuan Song, Cheng Deng

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments carried out on two popular large-scale tasks including Euclidean and semantic nearest neighbor search demonstrate that the proposed CBQ method enjoys the strong table complementarity and significantly outperforms the state-of-the-arts, with up to 57.76% performance gains relatively.
Researcher Affiliation Academia 1 State Key Lab of Software Development Environment, Beihang University, China 2 Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, China 3 School of Electronic Engineering, Xidian University, China
Pseudocode Yes Algorithm 1 Complementary Binary Quantization (CBQ).
Open Source Code No The paper does not provide any statement or link indicating that the source code for the methodology is open-source or available.
Open Datasets Yes In the experiments, we randomly select 10,000 and 1,000 samples as the training and the testing set respectively. ... We employ the two widely-used datasets SIFT-1M and GIST-1M [Jegou et al., 2011] ... we choose two widely-used large-scale image datasets: CIFAR-10 and NUS-WIDE.
Dataset Splits No The paper mentions training and testing sets, but does not explicitly describe a validation set or its split.
Hardware Specification No The paper does not specify the exact hardware (e.g., GPU/CPU models, memory) used for running experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies.
Experiment Setup Yes To start the algorithm, we initialize the prototypes P and the assignment m i for each samples using the classical K-means algorithm on the training data set. The number of clusters (or prototypes) is set to M = L 2b at first. Based on the initialization, we also estimate the scaling variable λ using the full binary codes in L hypercubes of b dimension... We set µ to 100 on SIFT-1M and 0.2 on GIST-1M. ... We set µ to 10 on CIFAR-10 and 20 on NUS-WIDE.