End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Faster-RCNN. However, DETR needs huge computational resources for training and inference due to the high-resolution spatial input. In this paper, a novel variant of transformer named Adaptive Clustering Transformer(ACT) has been proposed to reduce the computation cost for high-resolution input. ACT cluster the query features adaptively using Locality Sensitive Hashing (LSH) and ap-proximate the query-key interaction using the prototype-key interaction. ACT can reduce the quadratic O(N2) complexity inside self-attention into O(NK) where K is the number of prototypes in each layer. ACT can be a drop-in module replacing the original self-attention module without any training. ACT achieves a good balance between accuracy and computation cost (FLOPs). The code is available as supplementary for the ease of experiment replication and verification. Code is released at \url{https://github.com/gaopengcuhk/SMCA-DETR/}
@article{arxiv.2011.09315,
title = {End-to-End Object Detection with Adaptive Clustering Transformer},
author = {Minghang Zheng and Peng Gao and Renrui Zhang and Kunchang Li and Xiaogang Wang and Hongsheng Li and Hao Dong},
journal= {arXiv preprint arXiv:2011.09315},
year = {2021}
}