# Towards Light Weight Object Detection System

Source: [Towards Light Weight Object Detection System](<https://www.sota2.com/research/paper/68fa6da31e209131cea3b0f7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:39:21.820Z

Authors: Dharma KC, Venkata Ravi Kiran Dayana, Meng-Lin Wu, Venkateswara Rao Cherukuri, Hau Hwang

Published: 2022-10-08T00:55:15.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.03861>)

[PDF](<https://arxiv.org/pdf/2210.03861.pdf>)