# Hyneter: Hybrid Network Transformer for Object Detection

Source: [Hyneter: Hybrid Network Transformer for Object Detection](<https://www.sota2.com/research/paper/68fa6e951e209131cea40d8b>)

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

Data updated: 2025-10-26T01:01:51.507Z

Authors: Dong Chen, Duoqian Miao, Xuerong Zhao

Published: 2023-02-18T15:39:53.000Z

## Abstract

In this paper, we point out that the essential differences between CNN-based and Transformer-based detectors, which cause the worse performance of small objects in Transformer-based methods, are the gap between local information and global dependencies in feature extraction and propagation. To address these differences, we propose a new vision Transformer, called Hybrid Network Transformer (Hyneter), after pre-experiments that indicate the gap causes CNN-based and Transformer-based methods to increase size-different objects result unevenly. Different from the divide and conquer strategy in previous methods, Hyneters consist of Hybrid Network Backbone (HNB) and Dual Switching module (DS), which integrate local information and global dependencies, and transfer them simultaneously. Based on the balance strategy, HNB extends the range of local information by embedding convolution layers into Transformer blocks, and DS adjusts excessive reliance on global dependencies outside the patch.

## 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/2302.09365>)

[PDF](<https://arxiv.org/pdf/2302.09365.pdf>)
