# TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors

Source: [TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors](<https://www.sota2.com/research/paper/68fa6f091e209131cea4376f>)

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

Data updated: 2025-10-26T01:11:39.114Z

Authors: Shaoyu Chen, Tianheng Cheng, Jiemin Fang, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang

Published: 2023-04-07T00:45:50.000Z

## Abstract

Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited computation, we propose a two-stage lightweight detection framework with extremely low computation complexity, termed as TinyDet. It enables high-resolution feature maps for dense anchoring to better cover small objects, proposes a sparsely-connected convolution for computation reduction, enhances the early stage features in the backbone, and addresses the feature misalignment problem for accurate small object detection. On the COCO benchmark, our TinyDet-M achieves 30.3 AP and 13.5 AP^s with only 991 MFLOPs, which is the first detector that has an AP over 30 with less than 1 GFLOPs; besides, TinyDet-S and TinyDet-L achieve promising performance under different computation limitation.

## 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/2304.03428>)

[PDF](<https://arxiv.org/pdf/2304.03428.pdf>)