Redundancy-resistant Generative Hashing for Image Retrieval

Authors: Changying Du, Xingyu Xie, Changde Du, Hao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results show that our new method can significantly boost the quality of learned codes and achieve state-of-the-art performance for image retrieval.
Researcher Affiliation Collaboration Changying Du1, Xingyu Xie2, Changde Du3, Hao Wang1 1 360 Search Lab, Beijing 100015, China 2 College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China 3 Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., repository links or explicit statements of code release) for its methodology.
Open Datasets Yes We evaluate the proposed method on two computer vision tasks: 1) Image generation/reconstruction on MNIST [Oliva and Torralba, 2001]; 2) Image retrieval on CIFAR10 [Krizhevsky, 2009] and Caltech-256 [Griffin et al., 2007].
Dataset Splits No The paper describes training and query/gallery splits for CIFAR-10 and Caltech-256 datasets but does not explicitly mention or specify a validation set split.
Hardware Specification No The paper mentions 'modern CPU/GPU' generally but does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes Parameter Settings For the compared methods, we use the implementations provided by their authors (Deep-SGH is implemented directly based on SGH) and set the parameters according to their original papers. Without explicit statement, 1) for our R-SGH, the prior parameter ρj is set to 0.5 for any j {1, .., K}, the threshold parameter ϵ is set to 0.05, and both δ and η are set to 0.01; and 2) for R-SGH and Deep SGH, the encoder and decoder network structures are set as [D-K-K-K] and [K-K-K-D] respectively, where D and K are the dimensions of input data and hash code respectively.