3D Object Detection Using Scale Invariant and Feature Reweighting Networks

Authors: Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang9267-9274

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.
Researcher Affiliation Academia Xin Zhao,1 Zhe Liu,2 Ruolan Hu,2 Kaiqi Huang1 1Center for Research on Intelligent System and Engineering Institute of Automation, Chinese Academy of Sciences, Beijing, China, 100190 2Huazhong University of Science and Technology, Wuhan, China, 430074
Pseudocode No The paper describes the network architecture and its components (Point-UNet, T-Net, Point-SENet) in detail, but it does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. (...) KITTI: The KITTI 3D object detection dataset contains 7481 training images and Velodyne Lidars. We follow the settings in (Qi et al. 2018) and split the dataset into training set and validation set with 3717 and 3769 samples, respectively. (...) SUN-RGBD: The SUN-RGBD dataset have 700 object categories, the training set and test set contains 5285 and 5050 images, respectively.
Dataset Splits Yes KITTI: The KITTI 3D object detection dataset contains 7481 training images and Velodyne Lidars. We follow the settings in (Qi et al. 2018) and split the dataset into training set and validation set with 3717 and 3769 samples, respectively.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory) used to run the experiments. It only mentions general components like 'Res Net-50' as a backbone feature extractor.
Software Dependencies No The paper mentions software components such as 'Yolo V3' and 'Res Net-50' and optimizers like 'Adam', but it does not specify any version numbers for programming languages (e.g., Python), deep learning frameworks (e.g., TensorFlow, PyTorch), or other libraries.
Experiment Setup Yes The learning rate is equal to 1e-4. During the training process, we freeze the first 185 layers and release all the layers after 50 epochs. The training is terminated after 100 epochs. (...) The Adam optimizer is adopted to optimize the deep neural networks with the learning rate of 0.001. The first exponential decay rate is equal to 0.95 and the second exponential decay rate is equal to 0.999.