Robust Iterative Quantization for Efficient

Authors: ℓp

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on benchmark datasets demonstrate that ITQ+ is overwhelmingly better than the original ITQ algorithm, especially when searching similarity in noisy data. ... 3 Experiment ... We carried out comprehensive experiments for similarity search. ... The results of ITQ+ and ITQ on two datasets with different binary code lengths are shown in Figure 2.
Researcher Affiliation Academia School of Software, Tsinghua University, Beijing 100084, China Northumbria University, Newcastle, NE1 8ST, UK
Pseudocode Yes Algorithm 1 Learning ITQ+ Input: Centered training data X; Parameters p 2 and q p; Output: Orthogonal matrix R;
Open Source Code No The paper does not provide any concrete access information (e.g., URL or explicit statement) to the source code for the described methodology.
Open Datasets Yes The first one is SIFT1M [J egou et al., 2011] which consists of 128-dimensional SIFT [Lowe, 2004] descriptors. ... The second dataset is GIST1M [J egou et al., 2011] which contains 960-dimensional GIST [Oliva and Torralba, 2001] descriptors.
Dataset Splits No The paper specifies training and query (test) set sizes but does not explicitly mention a distinct validation set or provide its split details.
Hardware Specification No The paper does not provide any specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup Yes Following the settings in [Gong et al., 2013; He et al., 2013], we use Recall@R as the metric... In addition, following the setting in [Jegou et al., 2010; Gong et al., 2013], we first centralize the data and perform a PCA to reduce the feature dimensionality to the length of binary codes. ... For ITQ+, we consistently set q = 1 when comparing to ITQ. ... For a fair comparison, we terminate the algorithm after 50 iterations in all experiments as suggested by ITQ.