SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation

arXiv:2310.05920v3 Announce Type: replace
Abstract: The ability to detect objects in images at varying scales has played a pivotal role in the design of modern object detectors. Despite considerable progress in removing hand-crafted components and simplifying the architecture with transformers, multi-scale feature maps and/or pyramid design remain a key factor for their empirical success. In this paper, we show that this reliance on either feature pyramids or an hierarchical backbone is unnecessary and a transformer-based detector with scale-aware attention enables …

abstract architecture arxiv components cs.cv design detection feature images maps modern object objects pivotal progress pyramid role scale scaling segmentation simple simplifying simplr transformer transformers type