Learning to Zoom and Unzoom
원문 초록
Many perception systems in mobile computing, autonomous navigation, and AR/VR face strict compute constraints that are particularly challenging for high-resolution input images. Previous works propose nonuniform downsamplers that "learn to zoom" on salient image regions, reducing compute while retaining task-relevant image information. However, for tasks with spatial labels (such as 2D/3D object detection and semantic segmentation), such distortions may harm performance. In this work (LZU), we "learn to zoom" in on the input image, compute spatial features, and then "unzoom" to revert any deformations. To enable efficient and differentiable unzooming, we approximate the zooming warp with a piecewise bilinear mapping that is invertible. LZU can be applied to any task with 2D spatial input and any model with 2D spatial features, and we demonstrate this versatility by evaluating on a variety of tasks and datasets: object detection on Argoverse-HD, semantic segmentation on Cityscapes, and monocular 3D object detection on nuScenes. Interestingly, we observe boosts in performance even when high-resolution sensor data is unavailable, implying that LZU can be used to "learn to upsample" as well.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Vision-based Lifting of 2D Object Detections for Automated Driving
SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding
Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping
The Meeseeks Mesh: Spatially Consistent 3D Adversarial Objects for BEV Detector
Multi-Class Road User Detection With 3+1D Radar in the View-of-Delft Dataset
Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDAR
토론
이 논문과 연결된 포럼 글이 아직 없습니다.