Object as Distribution
This addresses object detection challenges like occlusion and uncertainty for applications such as autonomous driving, but appears incremental as it builds on existing representations.
The paper tackles object detection by proposing a new representation based on the bivariate normal distribution, which shows robust detection of highly-overlapping objects and potential for improved downstream tasks like instance segmentation, with qualitative evaluation for detection and quantitative evaluation for segmentation.
Object detection is a critical part of visual scene understanding. The representation of the object in the detection task has important implications on the efficiency and feasibility of annotation, robustness to occlusion, pose, lighting, and other visual sources of semantic uncertainty, and effectiveness in real-world applications (e.g., autonomous driving). Popular object representations include 2D and 3D bounding boxes, polygons, splines, pixels, and voxels. Each have their strengths and weakness. In this work, we propose a new representation of objects based on the bivariate normal distribution. This distribution-based representation has the benefit of robust detection of highly-overlapping objects and the potential for improved downstream tracking and instance segmentation tasks due to the statistical representation of object edges. We provide qualitative evaluation of this representation for the object detection task and quantitative evaluation of its use in a baseline algorithm for the instance segmentation task.