Update README.md

README.md

@@ -1,3 +1,37 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+# UNIP
+
+This repository contains the official pre-trained checkpoints of the paper "[UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation](https://arxiv.org/abs/2502.02257)".
+
+
+## 📖 Introduction
+
+![architecture_v8_00](imgs/architecture.png)
+
+In this work, we first benchmark the infrared semantic segmentation performance of various pre-training methods and reveal several phenomena distinct from the RGB domain. Next, our layerwise analysis of pre-trained attention maps uncovers that: (1) There are three typical attention patterns (local, hybrid, and global); (2) Pre-training tasks notably influence the pattern distribution across layers; (3) The hybrid pattern is crucial for semantic segmentation as it attends to both nearby and foreground elements; (4) The texture bias impedes model generalization in infrared tasks. Building on these insights, we propose **UNIP,** a **UN**ified **I**nfrared **P**re-training framework, to enhance the pre-trained model performance. This framework uses the hybrid-attention distillation NMI-HAD as the pre-training target, a large-scale mixed dataset InfMix for pre-training, and a last-layer feature pyramid network LL-FPN for fine-tuning.
+
+![distill_query_attn_v2_00](imgs/distill_query_attn.png)
+
+Experimental results show that UNIP outperforms various pre-training methods by up to **13.5%** in average mIoU on three infrared segmentation tasks, evaluated using fine-tuning and linear probing metrics. UNIP-S achieves performance on par with MAE-L while requiring only **1/10** of the computational cost. Furthermore, UNIP significantly surpasses state-of-the-art (SOTA) infrared or RGB segmentation methods and demonstrates the broad potential for application in other modalities, such as RGB and depth.
+
+<img src="imgs/benchmark.png" alt="benchmark" style="zoom: 67%;" />
+
+## 🛠️ Usage
+Please refer to the [GitHub repository](https://github.com/casiatao/UNIP).
+
+
+## Citation
+If you find this repository helpful, please consider citing:
+```bibtex
+@inproceedings{
+  zhang2025unip,
+  title={{UNIP}: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation},
+  author={Tao Zhang and Jinyong Wen and Zhen Chen and Kun Ding and Shiming Xiang and Chunhong Pan},
+  booktitle={The Thirteenth International Conference on Learning Representations},
+  year={2025},
+  url={https://openreview.net/forum?id=Xq7gwsnhPT}
+}
+```