GM-MLIC: Graph Matching based Multi-Label Image Classification

Authors: Yanan Wu, He Liu, Songhe Feng, Yi Jin, Gengyu Lyu, Zizhang Wu

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on various image datasets demonstrate the superiority of our proposed method.
Researcher Affiliation Collaboration Yanan Wu1 , He Liu1 , Songhe Feng1 , Yi Jin1 , Gengyu Lyu1 and Zizhang Wu2 1Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology, Beijing Jiaotong University 2Zongmu Technology
Pseudocode No The paper describes the proposed method in detail but does not include structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology.
Open Datasets Yes Results on VOC 2007. Pascal VOC 2007 [Everingham et al., 2010] is the most widely used dataset to evaluate the MLIC task... Results on MS-COCO. Microsoft COCO [Lin et al., 2014] contains a training set... Results on NUS-WIDE. The NUS-WIDE dataset [Chua et al., 2009] contains...
Dataset Splits Yes Microsoft COCO [Lin et al., 2014] contains a training set of 82,081 images and a validation set of 40,137 images
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No All modules are implemented in Py Torch... we apply Faster R-CNN (resnet50-fpn) [Ren et al., 2016]... we adopt 300-dim GloVe [Pennington et al., 2014]. No version numbers are given for PyTorch, Faster R-CNN, or GloVe.
Experiment Setup Yes During training, the input images are randomly cropped and resized into 448 448 with random horizontal flips for data augmentation. All modules are implemented in Py Torch and the optimizer is SGD with momentum 0.9. Weight decay is 10 4. The initial learning rate is 0.01, which decays by a factor of 10 for every 30 epochs. And the hyperparameter β in the Eq. (15) is set to 0 in VOC 2007 dataset and 0.4 in both MS-COCO and NUS-WIDE datasets. In our experiments, k is 2 and the output dimension of the corresponding convolution module is 512 and 256, respectively.