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 pyramid designs remain a key factor for their empirical success. In this paper, we show that shifting the multiscale inductive bias into the attention mechanism can work well, resulting in a plain detector `SimPLR' whose backbone and detection head are both non-hierarchical and operate on single-scale features. We find through our experiments that SimPLR with scale-aware attention is plain and simple architecture, yet competitive with multi-scale vision transformer alternatives. Compared to the multi-scale and single-scale state-of-the-art, our model scales better with bigger capacity (self-supervised) models and more pre-training data, allowing us to report a consistently better accuracy and faster runtime for object detection, instance segmentation, as well as panoptic segmentation. Code is released at https://github.com/kienduynguyen/SimPLR.
@article{arxiv.2310.05920,
title = {SimPLR: A Simple and Plain Transformer for Efficient Object Detection and Segmentation},
author = {Duy-Kien Nguyen and Martin R. Oswald and Cees G. M. Snoek},
journal= {arXiv preprint arXiv:2310.05920},
year = {2025}
}