update readme

Author: zhaoyian

README.md

@@ -27,36 +27,37 @@ English | [简体中文](README_cn.md)
 </p>
 
 ---
-<details>
-<summary>Fig</summary>
 
-![ppdetr_overview](https://github.com/lyuwenyu/RT-DETR/assets/17582080/737f0d94-e028-4793-967e-201bdde57a5a)
-</details>
+<div align="center">
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/0ede1dc1-a854-43b6-9986-cf9090f11a61" width=500 >
+</div>
 
 
 
-This is the official implementation of the paper "[DETRs Beat YOLOs on Real-time Object Detection](https://arxiv.org/abs/2304.08069)".
 
+This is the official implementation of the paper "[DETRs Beat YOLOs on Real-time Object Detection](https://arxiv.org/abs/2304.08069)".
 
-## Updates!!!
-- \[2024.01.23\] Fix difference on data augmentation with paper in rtdetr_pytorch [#84](https://github.com/lyuwenyu/RT-DETR/commit/5dc64138e439247b4e707dd6cebfe19d8d77f5b1)
-- \[2023.11.07\] Add pytorch *rtdetr_r34vd* for requests [#107](https://github.com/lyuwenyu/RT-DETR/issues/107), [#114](https://github.com/lyuwenyu/RT-DETR/issues/114)
-- \[2023.11.05\] upgrade the logic of `remap_mscoco_category` to facilitate training of custom datasets, see detils in [*Train custom data*](./rtdetr_pytorch/) part. [#81](https://github.com/lyuwenyu/RT-DETR/commit/95fc522fd7cf26c64ffd2ad0c622c392d29a9ebf)
-- \[2023.10.23\] Add [*discussion for deployments*](https://github.com/lyuwenyu/RT-DETR/issues/95), supported onnxruntime, TensorRT, openVINO
-- \[2023.10.12\] Add tuning code for pytorch version, now you can tuning rtdetr based on pretrained weights
-- \[2023.09.19\] Upload [*pytorch weights*](https://github.com/lyuwenyu/RT-DETR/issues/42) convert from paddle version
-- \[2023.08.24] Release rtdetr-18 pretrained models on objects365. *49.2 mAP* and *217 FPS*
-- \[2023.08.22\] Upload *[rtdetr_pytorch](./rtdetr_pytorch/)* source code. Please enjoy it ❤️
-- \[2023.08.15\] Release rtdetr-r101 pretrained models on objects365. *56.2 mAP* and *74 FPS*
-- \[2023.07.30\] Release rtdetr-r50 pretrained models on objects365. *55.3 mAP* and *108 FPS*
-- \[2023.07.28\] Fix some bugs, and add some comments. [1](https://github.com/lyuwenyu/RT-DETR/pull/14), [2](https://github.com/lyuwenyu/RT-DETR/commit/3b5cbcf8ae3b907e6b8bb65498a6be7c6736eabc)
-- \[2023.07.13\] Upload [*training logs on coco*](https://github.com/lyuwenyu/RT-DETR/issues/8)
-- \[2023.05.17\] Release RT-DETR-R18, RT-DETR-R34, RT-DETR-R50-m（example for scaled)
-- \[2023.04.17\] Release RT-DETR-R50, RT-DETR-R101, RT-DETR-L, RT-DETR-X
 
-## Implementations
-- rtdetr paddle: [code](./rtdetr_paddle), [weights](./rtdetr_paddle)
-- rtdetr pytorch: [code](./rtdetr_pytorch), [weights](./rtdetr_pytorch)
+## 🚀 Updates
+- \[2024.02.27\] Our work has been accepted to CVPR 2024!
+- \[2024.01.23\] Fix difference on data augmentation with paper in rtdetr_pytorch [#84](https://github.com/lyuwenyu/RT-DETR/commit/5dc64138e439247b4e707dd6cebfe19d8d77f5b1).
+- \[2023.11.07\] Add pytorch ✅ *rtdetr_r34vd* for requests [#107](https://github.com/lyuwenyu/RT-DETR/issues/107), [#114](https://github.com/lyuwenyu/RT-DETR/issues/114).
+- \[2023.11.05\] Upgrade the logic of `remap_mscoco_category` to facilitate training of custom datasets, see detils in [*Train custom data*](./rtdetr_pytorch/) part. [#81](https://github.com/lyuwenyu/RT-DETR/commit/95fc522fd7cf26c64ffd2ad0c622c392d29a9ebf).
+- \[2023.10.23\] Add [*discussion for deployments*](https://github.com/lyuwenyu/RT-DETR/issues/95), supported onnxruntime, TensorRT, openVINO.
+- \[2023.10.12\] Add tuning code for pytorch version, now you can tuning rtdetr based on pretrained weights.
+- \[2023.09.19\] Upload ✅ [*pytorch weights*](https://github.com/lyuwenyu/RT-DETR/issues/42) convert from paddle version.
+- \[2023.08.24] Release RT-DETR-R18 pretrained models on objects365. *49.2 mAP* and *217 FPS*.
+- \[2023.08.22\] Upload ✅ [*rtdetr_pytorch*](./rtdetr_pytorch/) source code. Please enjoy it!
+- \[2023.08.15\] Release RT-DETR-R101 pretrained models on objects365. *56.2 mAP* and *74 FPS*.
+- \[2023.07.30\] Release RT-DETR-R50 pretrained models on objects365. *55.3 mAP* and *108 FPS*.
+- \[2023.07.28\] Fix some bugs, and add some comments. [1](https://github.com/lyuwenyu/RT-DETR/pull/14), [2](https://github.com/lyuwenyu/RT-DETR/commit/3b5cbcf8ae3b907e6b8bb65498a6be7c6736eabc).
+- \[2023.07.13\] Upload ✅ [*training logs on coco*](https://github.com/lyuwenyu/RT-DETR/issues/8).
+- \[2023.05.17\] Release RT-DETR-R18, RT-DETR-R34, RT-DETR-R50-m（example for scaled).
+- \[2023.04.17\] Release RT-DETR-R50, RT-DETR-R101, RT-DETR-L, RT-DETR-X.
+
+## 📍 Implementations
+- 🔥 RT-DETR paddle: [code](./rtdetr_paddle), [weights](./rtdetr_paddle)
+- 🔥 RT-DETR pytorch: [code](./rtdetr_pytorch), [weights](./rtdetr_pytorch)
 
 
 | Model | Epoch | Input shape | Dataset | $AP^{val}$ | $AP^{val}_{50}$| Params(M) | FLOPs(G) | T4 TensorRT FP16(FPS)
@@ -76,19 +77,30 @@ This is the official implementation of the paper "[DETRs Beat YOLOs on Real-time
 - `COCO + Objects365` in the table means finetuned model on COCO using pretrained weights trained on Objects365.
 
 
-## Introduction
-We propose a **R**eal-**T**ime **DE**tection **TR**ansformer (RT-DETR, aka RTDETR), the first real-time end-to-end object detector to our best knowledge. Our RT-DETR-L achieves 53.0% AP on COCO val2017 and 114 FPS on T4 GPU, while RT-DETR-X achieves 54.8% AP and 74 FPS, outperforming all YOLO detectors of the same scale in both speed and accuracy. Furthermore, our RT-DETR-R50 achieves 53.1% AP and 108 FPS, outperforming DINO-Deformable-DETR-R50 by 2.2% AP in accuracy and by about 21 times in FPS. 
+## 💡 Introduction
+We propose a **R**eal-**T**ime **DE**tection **TR**ansformer (RT-DETR, aka RTDETR), the first real-time end-to-end object detector to our best knowledge. Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP.
+<div align="center">
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/c211a164-ddce-4084-8b71-fb73f29f363b" width=500 >
+</div>
+
+## 🦄 Performance
+
+### 🏕️ Complex Scenarios
+<div align="center">
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/52743892-68c8-4e53-b782-9f89221739e4" width=500 >
+</div>
+
+### 🌋 Difficult Conditions
 <div align="center">
-  <!-- <img src="https://github.com/PaddlePaddle/PaddleDetection/assets/17582080/3184a08e-aa4d-49cf-9079-f3695c4cc1c3" width=300 /> -->
-  <img src="https://github.com/lyuwenyu/RT-DETR/assets/17582080/42636690-1ecf-4647-b075-842ecb9bc562" width=500 >
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/213cf795-6da6-4261-8549-11947292d3cb" width=500 >
 </div>
 
 ## Citation
 If you use `RT-DETR` in your work, please use the following BibTeX entries:
 ```
 @misc{lv2023detrs,
       title={DETRs Beat YOLOs on Real-time Object Detection},
-      author={Wenyu Lv and Shangliang Xu and Yian Zhao and Guanzhong Wang and Jinman Wei and Cheng Cui and Yuning Du and Qingqing Dang and Yi Liu},
+      author={Yian Zhao and Wenyu Lv and Shangliang Xu and Jinman Wei and Guanzhong Wang and Qingqing Dang and Yi Liu and Jie Chen},
       year={2023},
       eprint={2304.08069},
       archivePrefix={arXiv},

README_cn.md

@@ -4,6 +4,10 @@
 
 This is the official implementation of the paper "[DETRs Beat YOLOs on Real-time Object Detection](https://arxiv.org/abs/2304.08069)".
 
+<div align="center">
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/0ede1dc1-a854-43b6-9986-cf9090f11a61" width=500 >
+</div>
+
 ## 最新动态
 
 - 发布RT-DETR-R50, RT-DETR-R101模型
@@ -13,26 +17,25 @@ This is the official implementation of the paper "[DETRs Beat YOLOs on Real-time
 
 
 ## 代码仓库
-- [rtdetr-paddle](./rtdetr_paddle)
-- [rtdetr-pytorch](./rtdetr_pytorch)
+- [RT-DETR-paddle](./rtdetr_paddle)
+- [RT-DETR--pytorch](./rtdetr_pytorch)
 
 
 ## 简介
 <!-- We propose a **R**eal-**T**ime **DE**tection **TR**ansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge. Specifically, we design an efficient hybrid encoder to efficiently process multi-scale features by decoupling the intra-scale interaction and cross-scale fusion, and propose IoU-aware query selection to improve the initialization of object queries. In addition, our proposed detector supports flexibly adjustment of the inference speed by using different decoder layers without the need for retraining, which facilitates the practical application of real-time object detectors. Our RT-DETR-L achieves 53.0% AP on COCO val2017 and 114 FPS on T4 GPU, while RT-DETR-X achieves 54.8% AP and 74 FPS, outperforming all YOLO detectors of the same scale in both speed and accuracy. Furthermore, our RT-DETR-R50 achieves 53.1% AP and 108 FPS, outperforming DINO-Deformable-DETR-R50 by 2.2% AP in accuracy and by about 21 times in FPS.  -->
-RT-DETR是第一个实时端到端目标检测器。具体而言，我们设计了一个高效的混合编码器，通过解耦尺度内交互和跨尺度融合来高效处理多尺度特征，并提出了IoU感知的查询选择机制，以优化解码器查询的初始化。此外，RT-DETR支持通过使用不同的解码器层来灵活调整推理速度，而不需要重新训练，这有助于实时目标检测器的实际应用。RT-DETR-L在COCO val2017上实现了53.0%的AP，在T4 GPU上实现了114FPS，RT-DETR-X实现了54.8%的AP和74FPS，在速度和精度方面都优于相同规模的所有YOLO检测器。RT-DETR-R50实现了53.1%的AP和108FPS，RT-DETR-R101实现了54.3%的AP和74FPS，在精度上超过了全部使用相同骨干网络的DETR检测器。
+RT-DETR是第一个实时端到端目标检测器。具体而言，我们设计了一个高效的混合编码器，通过解耦尺度内交互和跨尺度融合来高效处理多尺度特征，并提出了IoU感知的查询选择机制，以优化解码器查询的初始化。此外，RT-DETR支持通过使用不同的解码器层来灵活调整推理速度，而不需要重新训练，这有助于实时目标检测器的实际应用。RT-DETR-R50在COCO val2017上实现了53.1%的AP，在T4 GPU上实现了108FPS，RT-DETR-R101实现了54.3%的AP和74FPS，在速度和精度方面都优于相同规模的所有YOLO检测器。使用Objects365预训练之后, RT-DETR-R50 和 RT-DETR-R101 分别实现了 55.3% 和 56.2% AP的精度.
 若要了解更多细节，请参考我们的论文[paper](https://arxiv.org/abs/2304.08069).
 
 <div align="center">
-  <img src="https://github.com/PaddlePaddle/PaddleDetection/assets/17582080/3184a08e-aa4d-49cf-9079-f3695c4cc1c3" width=500 />
+  <img src="https://github.com/lyuwenyu/RT-DETR/assets/77494834/c211a164-ddce-4084-8b71-fb73f29f363b" width=500 >
 </div>
 
-
 ## 引用RT-DETR
 如果需要在你的研究中使用RT-DETR，请通过以下方式引用我们的论文：
 ```
 @misc{lv2023detrs,
       title={DETRs Beat YOLOs on Real-time Object Detection},
-      author={Wenyu Lv and Shangliang Xu and Yian Zhao and Guanzhong Wang and Jinman Wei and Cheng Cui and Yuning Du and Qingqing Dang and Yi Liu},
+      author={Yian Zhao and Wenyu Lv and Shangliang Xu and Jinman Wei and Guanzhong Wang and Qingqing Dang and Yi Liu and Jie Chen},
       year={2023},
       eprint={2304.08069},
       archivePrefix={arXiv},