Deep Multiple Instance Hashing for Object-based Image Retrieval

Authors: Wanqing Zhao, Ziyu Guan, Hangzai Luo, Jinye Peng, Jianping Fan

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on three benchmark datasets demonstrate the learned hash codes well preserve the object-level similarity and DMIH outperforms baselines on both single-object and multi-object queries.
Researcher Affiliation Academia Wanqing Zhao, Ziyu Guan , Hangzai Luo, Jinye Peng School of information and technology Northwestern University, Shaanxi, China {zhaowanqing,ziyuguan,hzluo,pjy}@nwu.edu.cn Jianping Fan Department of Computer Science UNC-Charlotte, NC28223, USA jfan@uncc.edu
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any information about open-source code for the methodology described.
Open Datasets Yes SIVAL. It is a benchmark dataset that emphasizes the task of object-based image retrieval. ... Pascal VOC 2007 [Everingham et al., 2007]. It contains 9,963 images with 20 different object categories. ... ILSVRC 2013 detection set. This dataset has a similar task and style with PASCAL VOC, but contains more images and categories.
Dataset Splits No The paper mentions training and testing sets, but does not specify a distinct validation dataset split. It mentions 'cross validation' for hyper-parameter tuning but not a data split for validation.
Hardware Specification Yes All the methods are run on a PC with NVIDIA GTX 1070 GPU, Inter Core i7-7700 CPU and 16GB memory.
Software Dependencies No The paper mentions using VGG-16 as a base network, but does not provide specific version numbers for any software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup Yes The hyper-parameter λ in Eq. (7) controls the balance between the two task losses. β and λ are set to 1.25 and 1 respectively by cross validation. ... We empirically set the objectness threshold θ = 0.7 for DMIH and its variants. Parameters of Pm H and DSRH are set to the best values reported.