@inproceedings{97b65a12a7834ce1909409acc602c274,
title = "EDSOD: An Encoder-Decoder, Diffusion-model, and Swin-Transformer-based Small Object Detector",
abstract = "Small object detection (SOD) given aerial images suffers from an information imbalance across different feature scales. This makes it extremely challenging to perform accurate SOD. Existing methods, e.g., Feature Pyramid Network (FPN)-based algorithms, focus on extracting high-resolution and low-resolution semantic features from different convolution layers. However, in deeper convolution layers, semantic feature misalignment and the loss of key information are inevitable. To tackle such issues, this work proposes a new encoder-decoder-based SOD framework with a Diffusion Model and Swin Transformer given aerial images. First, we reformulate an SOD task as a Noise-to-Box process. We then construct an encoder-decoder-based framework by using a diffusion model and Swin Transformer for dynamic bounding box generation. We introduce a decoupling training and inferencing strategy to recognize and locate small objects accurately. We finally evaluate the proposed framework on several public benchmarks. The experimental results well show its better SOD performance than the state of the art. Code is available at https://github.com/BrainPotter/EDSOD.",
keywords = "Small object detection, Swin Transformer, aerial images, diffusion model, encoder-decoder framework",
author = "Junnian Li and Zhou, \{Meng Chu\} and Zhengcai Cao",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2025 ; Conference date: 19-10-2025 Through 25-10-2025",
year = "2025",
doi = "10.1109/IROS60139.2025.11247171",
language = "English (US)",
series = "IEEE International Conference on Intelligent Robots and Systems ",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1659--1665",
editor = "Christian Laugier and Alessandro Renzaglia and Nikolay Atanasov and Stan Birchfield and Grzegorz Cielniak and \{De Mattos\}, Leonardo and Laura Fiorini and Philippe Giguere and Kenji Hashimoto and Javier Ibanez-Guzman and Tetsushi Kamegawa and Jinoh Lee and Giuseppe Loianno and Kevin Luck and Hisataka Maruyama and Philippe Martinet and Hadi Moradi and Urbano Nunes and Julien Pettre and Alberto Pretto and Tommaso Ranzani and Arne Ronnau and Silvia Rossi and Elliott Rouse and Fabio Ruggiero and Olivier Simonin and Danwei Wang and Ming Yang and Eiichi Yoshida and Huijing Zhao",
booktitle = "IROS 2025 - 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, Conference Proceedings",
address = "United States",
}