TL;DR
This paper introduces a multi-resolution progressive query refinement framework for bird's-eye-view semantic segmentation in autonomous driving, utilizing residual learning and feature interaction to improve global and local scene understanding.
Contribution
The paper proposes a novel multi-resolution query refinement method with residual learning and feature interaction for BEV semantic segmentation, outperforming state-of-the-art models.
Findings
Outperforms SOTA models in IoU metric on a large-scale dataset.
Effective global and local feature capture through progressive query refinement.
Enhanced feature interaction across images and levels improves segmentation accuracy.
Abstract
Expressing images with Multi-Resolution (MR) features has been widely adopted in many computer vision tasks. In this paper, we introduce the MR concept into Bird's-Eye-View (BEV) semantic segmentation for autonomous driving. This introduction enhances our model's ability to capture both global and local characteristics of driving scenes through our proposed residual learning. Specifically, given a set of MR BEV query maps, the lowest resolution query map is initially updated using a View Transformation (VT) encoder. This updated query map is then upscaled and merged with a higher resolution query map to undergo further updates in a subsequent VT encoder. This process is repeated until the resolution of the updated query map reaches the target. Finally, the lowest resolution map is added to the target resolution to generate the final query map. During training, we enforce both the lowest…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsSparse Evolutionary Training · ALIGN
