Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation of the self-attention layers used in the transformer architecture. This approximation reduces the latency of the classification system while incurring minimal loss in accuracy. We also present a method that uses a transformer encoder layer for multi-resolution feature fusion. This feature fusion improves the accuracy of the state-of-the-art lightweight object detection system without significantly increasing the number of parameters. Finally, we provide an abstraction for the transformer architecture called Generalized Transformer (gFormer) that can guide the design of novel transformer-like architectures.
@article{arxiv.2210.03861,
title = {Towards Light Weight Object Detection System},
author = {Dharma KC and Venkata Ravi Kiran Dayana and Meng-Lin Wu and Venkateswara Rao Cherukuri and Hau Hwang},
journal= {arXiv preprint arXiv:2210.03861},
year = {2022}
}