Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition

Authors: Tianshui Chen, Liang Lin, Riquan Chen, Yang Wu, Xiaonan Luo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on the widely used Caltech UCSD bird dataset demonstrate the superiority of our KERL framework over existing state-of-the-art methods.
Researcher Affiliation Collaboration 1 Sun Yat-sen University, China 2 Sense Time Research, China 3 Guilin University of Electronic Technology, China
Pseudocode No The paper describes the GGNN propagation process mathematically and provides an overall pipeline diagram, but it does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (like a repository link or an explicit statement of code release) for its own methodology.
Open Datasets Yes We evaluate our KERL framework and the competing methods on the Caltech-UCSD bird dataset [Wah et al., 2011] that is the most widely used benchmark for fine-grained image classification.
Dataset Splits No The dataset covers 200 species of birds, which contains 5,994 images for training and 5,794 for test. While training and testing sizes are given, there is no explicit mention of a separate validation set split with specific sizes or percentages.
Hardware Specification No The paper mentions implementing models with VGG16-Net and using convolutional neural networks, but it does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments.
Software Dependencies No The paper mentions using VGG16-Net, a compact bilinear model, SGD, and ADAM, but it does not provide specific version numbers for any software or libraries.
Experiment Setup Yes The dimension of the hidden state is set to 10 and that of the output feature is set to 5. The iteration time T is set to 5. The KERL framework is jointly trained using the cross-entropy loss. All components of the framework are trained with SGD except GGNN that is trained with ADAM following [Marino et al., 2017].