{"id":33120464,"url":"https://github.com/YeRen123455/Infrared-Small-Target-Detection","last_synced_at":"2025-11-16T09:01:20.055Z","repository":{"id":48165004,"uuid":"368468407","full_name":"YeRen123455/Infrared-Small-Target-Detection","owner":"YeRen123455","description":null,"archived":false,"fork":false,"pushed_at":"2023-05-13T04:52:42.000Z","size":35744,"stargazers_count":285,"open_issues_count":19,"forks_count":42,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-05-14T00:54:19.587Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YeRen123455.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-05-18T09:12:37.000Z","updated_at":"2024-05-13T09:16:26.000Z","dependencies_parsed_at":"2023-01-21T22:48:00.846Z","dependency_job_id":null,"html_url":"https://github.com/YeRen123455/Infrared-Small-Target-Detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/YeRen123455/Infrared-Small-Target-Detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeRen123455%2FInfrared-Small-Target-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeRen123455%2FInfrared-Small-Target-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeRen123455%2FInfrared-Small-Target-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeRen123455%2FInfrared-Small-Target-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeRen123455","download_url":"https://codeload.github.com/YeRen123455/Infrared-Small-Target-Detection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeRen123455%2FInfrared-Small-Target-Detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284684461,"owners_count":27046675,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-16T02:00:05.974Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-11-15T04:00:42.921Z","updated_at":"2025-11-16T09:01:20.047Z","avatar_url":"https://github.com/YeRen123455.png","language":"Python","funding_links":[],"categories":["Infrared Image Datasets","Anti-UAV Datasets"],"sub_categories":[],"readme":"# Dense Nested Attention Network for Infrared Small Target Detection\n\n## Good News! Our paper has been accepted by `IEEE Transaction on Image Processing`. Our team will release more interesting works and applications on SIRST soon. Please keep following our repository.\n\n![outline](overall_structure.png)\n\n## Algorithm Introduction\n\nDense Nested Attention Network for Infrared Small Target Detection, Boyang Li, Chao Xiao, Longguang Wang, and Yingqian Wang, arxiv 2021 [[Paper]](https://arxiv.org/pdf/2106.00487.pdf)\n\nWe propose a dense nested attention network (DNANet) to achieve accurate single-frame infrared small target detection and develop an open-sourced infrared small target dataset (namely, NUDT-SIRST) in this paper. Experiments on both public (e.g., NUAA-SIRST, NUST-SIRST) and our self-developed datasets demonstrate the effectiveness of our method. The contribution of this paper are as follows:\n\n1. We propose a dense nested attention network (namely, DNANet) to maintain small targets in deep layers.\n\n2. An open-sourced dataset (i.e., NUDT-SIRST) with rich targets.\n\n3. Performing well on all existing SIRST datasets.\n\n## Dataset Introduction\n\nNUDT-SIRST is a synthesized dataset, which contains 1327 images with resolution of 256x256. The advantage of synthesized dataset compared to real dataset lies in three aspets:\n\n1. Accurate annotations.\n\n2. Massive generation with low cost (i.e., time and money).\n\n3. Numerous categories of target, rich target sizes, diverse clutter backgrounds.\n\n## Citation\n\nIf you find the code useful, please consider citing our paper using the following BibTeX entry.\n\n```\n@article{DNANet,\n  title={Dense nested attention network for infrared small target detection},\n  author={Li, Boyang and Xiao, Chao and Wang, Longguang and Wang, Yingqian and Lin, Zaiping and Li, Miao and An, Wei and Guo, Yulan},\n  journal={IEEE Transactions on Image Processing},\n  year={2023},\n  volume={32},\n  pages={1745-1758},\n  publisher={IEEE}\n}\n```\n\n## Prerequisite\n* Tested on Ubuntu 16.04, with Python 3.7, PyTorch 1.7, Torchvision 0.8.1, CUDA 11.1, and 1x NVIDIA 3090 and also \n\n* Tested on Windows 10  , with Python 3.6, PyTorch 1.1, Torchvision 0.3.0, CUDA 10.0, and 1x NVIDIA 1080Ti.\n\n* [The NUDT-SIRST download dir](https://pan.baidu.com/s/1WdA_yOHDnIiyj4C9SbW_Kg?pwd=nudt) (Extraction Code: nudt)\n\n* [The NUAA-SIRST download dir](https://github.com/YimianDai/sirst) [[ACM]](https://arxiv.org/pdf/2009.14530.pdf)\n\n* [The NUST-SIRST download dir](https://github.com/wanghuanphd/MDvsFA_cGAN) [[MDvsFA]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Miss_Detection_vs._False_Alarm_Adversarial_Learning_for_Small_Object_ICCV_2019_paper.pdf)\n\n## Usage\n\n#### On windows:\n\n```\nClick on train.py and run it. \n```\n\n#### On Ubuntu:\n\n#### 1. Train.\n\n```bash\npython train.py --base_size 256 --crop_size 256 --epochs 1500 --dataset [dataset-name] --split_method 50_50 --model [model name] --backbone resnet_18  --deep_supervision True --train_batch_size 16 --test_batch_size 16 --mode TXT\n\n```\n#### 2. Test.\n\n```bash\npython test.py --base_size 256 --crop_size 256 --st_model [trained model path] --model_dir [model_dir] --dataset [dataset-name] --split_method 50_50 --model [model name] --backbone resnet_18  --deep_supervision True --test_batch_size 1 --mode TXT \n```\n\n#### (Optional 1) Visulize your predicts.\n```bash\npython visulization.py --base_size 256 --crop_size 256 --st_model [trained model path] --model_dir [model_dir] --dataset [dataset-name] --split_method 50_50 --model [model name] --backbone resnet_18  --deep_supervision True --test_batch_size 1 --mode TXT \n```\n\n#### (Optional 2) Test and visulization.\n```bash\npython test_and_visulization.py --base_size 256 --crop_size 256 --st_model [trained model path] --model_dir [model_dir] --dataset [dataset-name] --split_method 50_50 --model [model name] --backbone resnet_18  --deep_supervision True --test_batch_size 1 --mode TXT \n```\n\n#### (Optional 3) Demo (with your own IR image).\n```bash\npython demo.py --base_size 256 --crop_size 256 --img_demo_dir [img_demo_dir] --img_demo_index [image_name]  --model [model name] --backbone resnet_18  --deep_supervision True --test_batch_size 1 --mode TXT  --suffix [img_suffix]\n\n```\n\n## Results and Trained Models\n#### Qualitative Results\n\n![outline](Qualitative_result.png)\n\n#### Quantative Results \n\non NUDT-SIRST\n\n| Model         | mIoU (x10(-2)) | Pd (x10(-2))|  Fa (x10(-6)) ||\n| ------------- |:-------------:|:-----:|:-----:|:-----:|\n| DNANet-VGG-10 | 85.23 | 96.95 | 6.782|\n| DNANet-ResNet-10| 86.36 | 97.39 | 6.897 |\n| DNANet-ResNet-18| 87.09 | 98.73 | 4.223 |\n| DNANet-ResNet-18| 88.61 | 98.42 | 4.30 | [[Weights]](https://drive.google.com/file/d/1NDvjOiWecfWNPaO12KeIgiJMTKSFS6wj/view?usp=sharing) |\n| DNANet-ResNet-34| 86.87 | 97.98 | 3.710 |\n\n\non NUAA-SIRST\n| Model         | mIoU (x10(-2)) | Pd (x10(-2))|  Fa (x10(-6)) ||\n| ------------- |:-------------:|:-----:|:-----:|:-----:|\n| DNANet-VGG-10 | 74.96 | 97.34 | 26.73 |\n| DNANet-ResNet-10| 76.24 | 97.71 | 12.80 |\n| DNANet-ResNet-18| 77.47 | 98.48 | 2.353 |\n| DNANet-ResNet-18| 79.26 | 98.48 | 2.30 | [[Weights]](https://drive.google.com/file/d/1W0jFN9ZlaIdGFemYKi34tmJfGxjUGCRc/view?usp=sharing) |\n| DNANet-ResNet-34| 77.54 | 98.10 | 2.510 |\n\non NUST-SIRST\n\n| Model         | mIoU (x10(-2)) | Pd (x10(-2))|  Fa (x10(-6)) ||\n| ------------- |:-------------:|:-----:|:-----:|:-----:|\n| DNANet-ResNet-18| 46.73 | 81.29 | 33.87 | [[Weights]](https://drive.google.com/file/d/1TF0bZRMsGuKzMhlHKH1LygScBveMcCS2/view?usp=sharing) |\n\n*This code is highly borrowed from [ACM](https://github.com/YimianDai/open-acm). Thanks to Yimian Dai.\n\n*The overall repository style is highly borrowed from [PSA](https://github.com/jiwoon-ahn/psa). Thanks to jiwoon-ahn.\n\n## Referrences\n\n1. Dai Y, Wu Y, Zhou F, et al. Asymmetric contextual modulation for infrared small target detection[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2021: 950-959. [[code]](https://github.com/YimianDai/open-acm) \n\n2. Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE transactions on medical imaging, 2019, 39(6): 1856-1867. [[code]](https://github.com/MrGiovanni/UNetPlusPlus)\n\n3. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778. [[code]](https://github.com/rwightman/pytorch-image-models)\n\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYeRen123455%2FInfrared-Small-Target-Detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYeRen123455%2FInfrared-Small-Target-Detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYeRen123455%2FInfrared-Small-Target-Detection/lists"}