SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filter
This work addresses semi-supervised 3D object detection for point cloud data, representing an incremental improvement over existing frameworks.
The paper tackled the problem of semi-supervised 3D object detection in point clouds by introducing a strict threshold and filter switching to retain only high-quality pseudo labels, resulting in superior performance on the KITTI dataset compared to state-of-the-art methods.
SSF3D modified the semi-supervised 3D object detection (SS3DOD) framework, which designed specifically for point cloud data. Leveraging the characteristics of non-coincidence and weak correlation of target objects in point cloud, we adopt a strategy of retaining only the truth-determining pseudo labels and trimming the other fuzzy labels with points, instead of pursuing a balance between the quantity and quality of pseudo labels. Besides, we notice that changing the filter will make the model meet different distributed targets, which is beneficial to break the training bottleneck. Two mechanism are introduced to achieve above ideas: strict threshold and filter switching. The experiments are conducted to analyze the effectiveness of above approaches and their impact on the overall performance of the system. Evaluating on the KITTI dataset, SSF3D exhibits superior performance compared to the current state-of-the-art methods. The code will be released here.