# CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection

Source: [CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection](<https://www.sota2.com/research/paper/68fa7a511e209131cea8268b>)

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

Data updated: 2025-10-26T05:17:11.038Z

Authors: Haolin Wei

Published: 2025-06-21T11:12:52.000Z

## Abstract

Convolutional neural networks (CNNs) have long been the cornerstone of target detection, but they are often limited by limited receptive fields, which hinders their ability to capture global contextual information. We re-examined the DETR-inspired detection head and found substantial redundancy in its self-attention module. To solve these problems, we introduced the Context-Gated Scale-Adaptive Detection Network (CSDN), a Transformer-based detection header inspired by human visual perception: when observing an object, we always concentrate on one site, perceive the surrounding environment, and glance around the object. This mechanism enables each region of interest (ROI) to adaptively select and combine feature dimensions and scale information from different patterns. CSDN provides more powerful global context modeling capabilities and can better adapt to objects of different sizes and structures. Our proposed detection head can directly replace the native heads of various CNN-based detectors, and only a few rounds of fine-tuning on the pre-trained weights can significantly improve the detection accuracy.

## 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/2506.17679>)

[PDF](<https://arxiv.org/pdf/2506.17679.pdf>)
