iLearn-Lab
/

MM26-ADGNet

@@ -1,197 +1,216 @@
----
-license: apache-2.0
-pipeline_tag: image-segmentation
-tags:
-  - infrared-small-target-detection
-  - multimodal
-  - vision-language
-  - pytorch
----
-<h1>ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection</h1>
-<p>
-  <b>Tongtong Wang</b><sup>1</sup>&nbsp;
-  <b>Mingzhu Xu</b><sup>1✉</sup>&nbsp;
-  <b>Chenglong Yu</b><sup>1</sup>&nbsp;
-  <b>Jing Wang</b><sup>1</sup>&nbsp;
-  <b>Xiaohui Lin</b><sup>1</sup>&nbsp;
-  <b>Weili Guan</b><sup>2</sup>
-</p>
-<p>
-  <sup>1</sup>School of Software, Shandong University<br>
-  <sup>2</sup>Harbin Institute of Technology, Shenzhen<br>
-  <sup>✉</sup>Corresponding author
-</p>
-<p>
-  <a href="<paper-link>">
-    <img src="https://img.shields.io/badge/ACM%20MM-2026-blue" alt="ACM MM 2026">
-  </a>
-  <a href="https://github.com/iLearn-Lab/MM26-ADGNet">
-    <img src="https://img.shields.io/badge/GitHub-MM26--ADGNet-black?logo=github" alt="GitHub">
-  </a>
-</p>
-## 📖 Model Description
-This repository provides the official model checkpoints for **ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection**, accepted by **ACM Multimedia 2026**.
-Infrared Small Target Detection aims to accurately segment weak and tiny targets from complex infrared backgrounds. Existing pure-vision methods rely mainly on pixel-level information, while existing vision-language methods commonly describe targets and backgrounds using a single textual prompt. Such a symmetric design overlooks the inherent semantic differences between sparse infrared targets and structurally complex backgrounds.
-ADGNet addresses this problem through three main components:
-- **Asymmetric Dual-text Prompt (ADP):** uses an abstract, image-independent target prompt and a detailed, image-dependent background prompt.
-- **Asymmetric Dual-Branch Interaction (ADBI):** independently performs target localization and background suppression using their corresponding textual priors.
-- **Adaptive Feature Aggregation (AFA):** dynamically fuses target-enhanced and background-suppressed features for accurate segmentation.
-The model uses the pretrained **CLIP ViT-B/16** text encoder to extract semantic representations from the target and background prompts.
----
-## 🏆 Available Checkpoints
-All ADGNet checkpoints are hosted in this Hugging Face model repository.
-Download the required checkpoint directly from the **Files and versions** section of this repository.
-|  Dataset   |                          Checkpoint                          |
-| :--------: | :----------------------------------------------------------: |
-|  IRSTD-1K  | [`ADGNet_mIoU_72.38_IRSTD-1K.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_72.38_IRSTD-1K.pth.tar) |
-| NUDT-SIRST | [`ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar) |
-|   SIRST    | [`ADGNet_mIoU_83.08_SIRST.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_83.08_SIRST.pth.tar) |
----
-## 🚀 Usage
-These checkpoints are designed to be used with the official ADGNet implementation:
-```text
-https://github.com/iLearn-Lab/MM26-ADGNet
-```
-### 1. Clone the Official Repository
-```bash
-git clone https://github.com/iLearn-Lab/MM26-ADGNet.git
-cd MM26-ADGNet
-```
-### 2. Prepare the Checkpoints
-Place the downloaded checkpoints in:
-```text
-MM26-ADGNet/
-└── SOTA_pth/
-    ├── ADGNet_mIoU_72.38_IRSTD-1K.pth.tar
-    ├── ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar
-    └── ADGNet_mIoU_83.08_SIRST.pth.tar
-```
-### 3. Prepare the CLIP Text Encoder
-ADGNet uses the pretrained **CLIP ViT-B/16** model:
-```bash
-git clone https://huggingface.co/openai/clip-vit-base-patch16
-```
-Update the local CLIP model path in the corresponding project configuration or source file before inference.
-### 4. Run Evaluation
-Example evaluation on IRSTD-1K:
-```bash
-python train.py \
-    --trainset "IRSTD-1K" \
-    --testset "IRSTD-1K" \
-    --dataset_dir "./datasets" \
-    --mode test \
-    --ckpt "./SOTA_pth/ADGNet_mIoU_72.38_IRSTD-1K.pth.tar"
-```
-Replace the dataset name and checkpoint path when evaluating on NUDT-SIRST or SIRST.
----
-## 📂 Dataset and Text Annotation Preparation
-The original infrared images and ground-truth masks are not included in this model repository. Please obtain **IRSTD-1K**, **NUDT-SIRST**, and **SIRST** from their respective official sources.
-The asymmetric text annotations used by ADGNet are released separately in our Hugging Face dataset repository:
-- **AITIR Text Annotations:** [`Download`](<huggingface-text-dataset-link>)
-After downloading the original datasets and text annotations, organize them according to the official ADGNet repository:
-```text
-datasets/
-├── IRSTD-1K/
-│   ├── images/
-│   ├── masks/
-│   ├── img_idx/
-│   └── text/
-├── NUDT-SIRST/
-│   ├── images/
-│   ├── masks/
-│   ├── img_idx/
-│   └── text/
-└── SIRST/
-    ├── images/
-    ├── masks/
-    ├── img_idx/
-    └── text/
-```
----
-## 🎯 Intended Use
-The released checkpoints are intended for:
-- Academic research on infrared small target detection
-- Reproduction of the results reported in the ADGNet paper
-- Evaluation on IRSTD-1K, NUDT-SIRST, and SIRST
-- Research on multimodal and text-guided infrared image segmentation
-- Comparison with other infrared small target detection methods
----
-## ⚠️ Limitations
-- The model requires both infrared images and corresponding textual prompts.
-- Detection performance may vary when applied to datasets or scenes that differ substantially from the training distribution.
-- The released checkpoints are designed for the dataset splits and evaluation settings used in the paper.
-- The model depends on the pretrained CLIP ViT-B/16 text encoder.
-- The original infrared datasets are subject to their respective licenses and terms of use.
----
-## 🔗 Related Resources
-- **GitHub Repository:** [iLearn-Lab/MM26-ADGNet](https://github.com/iLearn-Lab/MM26-ADGNet)
-- **Paper:** [`ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection`](<paper-link>)
-- **Text Annotations:** [`AITIR Text Annotations`](<huggingface-text-dataset-link>)
----
-## 📚 Citation
-If you find ADGNet or the released checkpoints useful in your research, please consider citing our paper:
-```bibtex
-```
-Please also consider checking out and citing our other related work:
-```bibtex
-```
----

+---
+license: apache-2.0
+pipeline_tag: image-segmentation
+tags:
+- infrared-small-target-detection
+- multimodal
+- vision-language
+- pytorch
+---
+<h1>ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection</h1>
+<p>
+  <b>Tongtong Wang</b><sup>1</sup>&nbsp;
+  <b>Mingzhu Xu</b><sup>1✉</sup>&nbsp;
+  <b>Chenglong Yu</b><sup>1</sup>&nbsp;
+  <b>Jing Wang</b><sup>1</sup>&nbsp;
+  <b>Xiaohui Lin</b><sup>1</sup>&nbsp;
+  <b>Weili Guan</b><sup>2</sup>
+</p>
+<p>
+  <sup>1</sup>School of Software, Shandong University<br>
+  <sup>2</sup>Harbin Institute of Technology, Shenzhen<br>
+  <sup>✉</sup>Corresponding author
+</p>
+<p>
+  <a href="https://huggingface.co/papers/2609.00853">
+    <img src="https://img.shields.io/badge/ACM%20MM-2026-blue" alt="ACM MM 2026">
+  </a>
+  <a href="https://github.com/iLearn-Lab/MM26-ADGNet">
+    <img src="https://img.shields.io/badge/GitHub-MM26--ADGNet-black?logo=github" alt="GitHub">
+  </a>
+</p>
+## 📖 Model Description
+This repository provides the official model checkpoints for **ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection**, accepted by **ACM Multimedia 2026**.
+Infrared Small Target Detection aims to accurately segment weak and tiny targets from complex infrared backgrounds. Existing pure-vision methods rely mainly on pixel-level information, while existing vision-language methods commonly describe targets and backgrounds using a single textual prompt. Such a symmetric design overlooks the inherent semantic differences between sparse infrared targets and structurally complex backgrounds.
+ADGNet addresses this problem through three main components:
+- **Asymmetric Dual-text Prompt (ADP):** uses an abstract, image-independent target prompt and a detailed, image-dependent background prompt.
+- **Asymmetric Dual-Branch Interaction (ADBI):** independently performs target localization and background suppression using their corresponding textual priors.
+- **Adaptive Feature Aggregation (AFA):** dynamically fuses target-enhanced and background-suppressed features for accurate segmentation.
+The model uses the pretrained **CLIP ViT-B/16** text encoder to extract semantic representations from the target and background prompts.
+---
+## 🏆 Available Checkpoints
+All ADGNet checkpoints are hosted in this Hugging Face model repository.
+Download the required checkpoint directly from the **Files and versions** section of this repository.
+|  Dataset   |                          Checkpoint                          |
+| :--------: | :----------------------------------------------------------: |
+|  IRSTD-1K  | [`ADGNet_mIoU_72.38_IRSTD-1K.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_72.38_IRSTD-1K.pth.tar) |
+| NUDT-SIRST | [`ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar) |
+|   SIRST    | [`ADGNet_mIoU_83.08_SIRST.pth.tar`](https://huggingface.co/iLearn-Lab/MM26-ADGNet/blob/main/ADGNet_mIoU_83.08_SIRST.pth.tar) |
+---
+## 🚀 Usage
+These checkpoints are designed to be used with the official ADGNet implementation:
+```text
+https://github.com/iLearn-Lab/MM26-ADGNet
+```
+### 1. Clone the Official Repository
+```bash
+git clone https://github.com/iLearn-Lab/MM26-ADGNet.git
+cd MM26-ADGNet
+```
+### 2. Prepare the Checkpoints
+Place the downloaded checkpoints in:
+```text
+MM26-ADGNet/
+└── SOTA_pth/
+    ├── ADGNet_mIoU_72.38_IRSTD-1K.pth.tar
+    ├── ADGNet_mIoU_95.53_NUDT-SIRST.pth.tar
+    └── ADGNet_mIoU_83.08_SIRST.pth.tar
+```
+### 3. Prepare the CLIP Text Encoder
+ADGNet uses the pretrained **CLIP ViT-B/16** model:
+```bash
+git clone https://huggingface.co/openai/clip-vit-base-patch16
+```
+Update the local CLIP model path in the corresponding project configuration or source file before inference.
+### 4. Run Evaluation
+Example evaluation on IRSTD-1K:
+```bash
+python train.py \
+    --trainset "IRSTD-1K" \
+    --testset "IRSTD-1K" \
+    --dataset_dir "./datasets" \
+    --mode test \
+    --ckpt "./SOTA_pth/ADGNet_mIoU_72.38_IRSTD-1K.pth.tar"
+```
+Replace the dataset name and checkpoint path when evaluating on NUDT-SIRST or SIRST.
+---
+## 📂 Dataset and Text Annotation Preparation
+The original infrared images and ground-truth masks are not included in this model repository. Please obtain **IRSTD-1K**, **NUDT-SIRST**, and **SIRST** from their respective official sources.
+The asymmetric text annotations used by ADGNet are released separately in our Hugging Face dataset repository:
+- **AITIR Text Annotations:** [`Download`](https://huggingface.co/datasets/iLearn-Lab/MM26-ADGNet-AITIR-Text)
+After downloading the original datasets and text annotations, organize them according to the official ADGNet repository:
+```text
+datasets/
+├── IRSTD-1K/
+│   ├── images/
+│   ├── masks/
+│   ├── img_idx/
+│   └── text/
+├── NUDT-SIRST/
+│   ├── images/
+│   ├── masks/
+│   ├── img_idx/
+│   └── text/
+└── SIRST/
+    ├── images/
+    ├── masks/
+    ├── img_idx/
+    └── text/
+```
+---
+## 🎯 Intended Use
+The released checkpoints are intended for:
+- Academic research on infrared small target detection
+- Reproduction of the results reported in the ADGNet paper
+- Evaluation on IRSTD-1K, NUDT-SIRST, and SIRST
+- Research on multimodal and text-guided infrared image segmentation
+- Comparison with other infrared small target detection methods
+---
+## ⚠️ Limitations
+- The model requires both infrared images and corresponding textual prompts.
+- Detection performance may vary when applied to datasets or scenes that differ substantially from the training distribution.
+- The released checkpoints are designed for the dataset splits and evaluation settings used in the paper.
+- The model depends on the pretrained CLIP ViT-B/16 text encoder.
+- The original infrared datasets are subject to their respective licenses and terms of use.
+---
+## 🔗 Related Resources
+- **GitHub Repository:** [iLearn-Lab/MM26-ADGNet](https://github.com/iLearn-Lab/MM26-ADGNet)
+- **Paper:** [`ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection`](https://huggingface.co/papers/2609.00853)
+- **Text Annotations:** [`AITIR Text Annotations`](https://huggingface.co/datasets/iLearn-Lab/MM26-ADGNet-AITIR-Text)
+---
+## 📚 Citation
+If you find ADGNet or the released checkpoints useful in your research, please consider citing our paper:
+```bibtex
+@inproceedings{wang2026adgnet,
+  title     = {ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection},
+  author    = {Wang, Tongtong and Xu, Mingzhu and Yu, Chenglong and Wang, Jing and Lin, Xiaohui and Guan, Weili},
+  booktitle = {Proceedings of the ACM International Conference on Multimedia},
+  year      = {2026},
+}
+```
+Please also consider checking out and citing our other related work:
+```bibtex
+@inproceedings{yu2026dgnet,
+  title     = {DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection},
+  author    = {Yu, Chenglong and Xu, Mingzhu and Wang, Jing and Wang, Tongtong and Miao, Pingping and Nie, Liqiang},
+  booktitle = {Proceedings of the ACM International Conference on Multimedia},
+  year      = {2026},
+}
+@article{11017756,
+  author  = {Xu, Mingzhu and Yu, Chenglong and Li, Zexuan and Tang, Haoyu and Hu, Yupeng and Nie, Liqiang},
+  journal = {IEEE Transactions on Geoscience and Remote Sensing},
+  title   = {HDNet: A Hybrid Domain Network With Multiscale High-Frequency Information Enhancement for Infrared Small-Target Detection},
+  year    = {2025},
+  volume  = {63},
+  pages   = {1--15},
+  doi     = {10.1109/TGRS.2025.3574962},
+}
+```
+---