JM-Net and Cluster-SVM for Aerial Scene Classification
Authors: Xiaoqiang Lu, Yuan Yuan, Jie Fang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our experiments, we use two challenging datasets, RSD and AID. RSD consists of 1005 pictures within 19 classes, and AID consists of 10000 pictures within 30 classes (some samples of AID dataset are showed in Figure 3). As we all know, aerial image has the characteristics of scale and direction changeable, so we can not use the images from the dataset only to train a robust Convolutional Neural Network effectively. To address this problem, the datasets are expanded according to the following steps: ... Table 7: The result of proposed method on RSD & AID |
| Researcher Affiliation | Academia | 1Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi an 710119, Shaanxi, China. 2University of the Chinese Academy of Sciences, 19A Yuquanlu, Beijing, 100047, China. |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any statements about the availability of open-source code or links to a code repository. |
| Open Datasets | No | The paper mentions using "RSD" and "AID" datasets but does not provide specific links, DOIs, repositories, or formal citations with authors and year for their public availability. It describes how they expanded the dataset but not how to access the original or expanded version. |
| Dataset Splits | No | The paper does not specify training, validation, or test dataset splits (e.g., percentages, sample counts, or predefined splits). |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments (e.g., specific GPU or CPU models, memory, or cloud instances). |
| Software Dependencies | No | The paper mentions general software or models like "Alex-Net" and "Caffe Net" but does not specify any software dependencies with version numbers (e.g., specific libraries, frameworks, or programming language versions used for implementation). |
| Experiment Setup | Yes | In our experiments, we use two challenging datasets, RSD and AID. ... 4.1 Choose the Parameters of JM-Net ... From Table II, it is obvious that 2048 dimension vectors are enough to represent the aerial scene images. when design the architecture of JM-Net, we make the output of JM-Net s last layer to be 2048 dimensions. ... From TABLE 3, It can be seen, when the ratio of 3 3 and 1 1 convolution filters are both 0.5, the classification accuracy reaches to the top. ... 4.2 Choose the Parameters of Cluster-SVM ... From the TABLE 4 and TABLE 5, we can see when the cluster number is about 1/8 of the amount of the overall images in the datasets, that the classification accuracy reaches the peak. Additionally, the parameter λ of Sim loss reflects the attention of the cluster strategy. From the TABLE 6 we can see that, when the λ is about 0.7, the experiment result reaches to the peak. |