昇思MindSpore开发板应用创新行动

#### 【活动说明】
基于香橙派开发板，提供系统化的案例、教程与支持，帮助开发者快速上手、快速入门、快速打造个性化应用。完成相关论文代码代码迁移与精度验证，并关联至对应论文的[Paper with code](https://paperswithcode.com/)， 待 **昇思MindSpore蓝色logo图标显示** 即完成任务。

#### 【活动奖品介绍】
Orange Pi AIpro采用昇腾AI技术路线，具体为4核64位处理器+AI处理器，集成图形处理器，支持8/20 TOPS AI算力，拥有8GB/16GB LPDDR4X，可以外接32GB/64GB/128GB/256GB eMMC模块，支持双4K高清输出。 Orange Pi AIpro引用了相当丰富的接口，包括两个HDMI输出、GPIO接口、Type-C电源接口、支持SATA/NVMe SSD 2280的M.2插槽、TF插槽、千兆网口、两个USB3.0、一个USB Type-C 3.0、一个Micro USB（串口打印调试功能）、两个MIPI摄像头、一个MIPI屏等，预留电池接口，可广泛适用于AI边缘计算、深度视觉学习及视频流AI分析、视频图像分析、自然语言处理、智能小车、机械臂、人工智能、无人机、云计算、AR/VR、智能安防、智能家居等领域，覆盖 AIoT各个行业。 Orange Pi AIpro支持Ubuntu、openEuler操作系统，满足大多数AI算法原型验证、推理应用开发的需求。[香橙派官网](http://www.orangepi.cn/html/hardWare/computerAndMicrocontrollers/details/Orange-Pi-5-Pro.html)

#### 【任务认领】
在下方评论区发送“任务序号+姓名”即可参加（例：任务1 王XX）
留言后即视为任务开始，任务时效为2个月，过期视为放弃任务

#### 【任务列表】

| 序号 | 论文名称 | 论文链接 | 代码仓 | 关联链接 |认领人|
| --- | ------------ | -------------- | ----------------- | ------------- |  ----------- | 
| 1 | PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers | [论文链接](https://arxiv.org/pdf/2206.02066.pdf) | [代码仓](https://github.com/XuJiacong/PIDNet) | [pwc链接](https://paperswithcode.com/paper/pidnet-a-real-time-semantic-segmentation) |秦鹏| 
| 2 | YOLO-World: Real-Time Open-Vocabulary Object Detection | [论文链接](https://arxiv.org/abs/2401.17270) | [代码仓](https://github.com/AILAB-CVC/YOLO-World) | [pwc链接](https://paperswithcode.com/paper/yolo-world-real-time-open-vocabulary-object) |王家一| 
| 3 | CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model | [论文链接](https://arxiv.org/abs/2304.04231) | [代码仓](https://github.com/dk-liang/CrowdCLIP) | [pwc链接](https://paperswithcode.com/paper/crowdclip-unsupervised-crowd-counting-via) |李柏坤| 
| 4 | Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining | [论文链接](https://arxiv.org/abs/2303.11880) | [代码仓](https://github.com/cschenxiang/NeRD-Rain) | [pwc链接](https://paperswithcode.com/paper/bidirectional-multi-scale-implicit-neural) | 蔡八斤| 
| 5 | PolyFormer: Referring Image Segmentation as Sequential Polygon Generation | [论文链接](https://arxiv.org/abs/2404.01547) | [代码仓](https://github.com/amazon-science/polygon-transformer) | [pwc链接](https://paperswithcode.com/paper/polyformer-referring-image-segmentation-as) | 张冠华| 
| 6 | Cost Aggregation for Open-Vocabulary Semantic Segmentation | [论文链接](https://doi.org/10.48550/arXiv.2303.11797) | [代码仓](https://github.com/KU-CVLAB/CAT-Seg.git) | [pwc链接](https://paperswithcode.com/paper/cat-seg-cost-aggregation-for-open-vocabulary) | 蒋雯鑫| 
| 7 | Zero-Reference Low-Light Enhancement via Physical Quadruple Priors | [论文链接](https://arxiv.org/abs/2403.12933) | [代码仓](https://github.com/daooshee/QuadPrior/) | [pwc链接](https://paperswithcode.com/paper/zero-reference-low-light-enhancement-via) |黄熠| 
| 8 | Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers | [论文链接](https://arxiv.org/abs/2303.14816) | [代码仓](https://github.com/ZhouHuang23/FSPNet) | [pwc链接](https://paperswithcode.com/paper/feature-shrinkage-pyramid-for-camouflaged) | 周陈铮| 
| 9 | EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything | [论文链接](https://arxiv.org/pdf/2312.00863.pdf) | [代码仓](https://github.com/yformer/EfficientSAM) | [pwc链接](https://paperswithcode.com/paper/efficientsam-leveraged-masked-image) | 黄蒙| 
| 10 | Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation | [论文链接](https://arxiv.org/abs/2312.04265) | [代码仓](https://github.com/w1oves/Rein) | [pwc链接](https://paperswithcode.com/paper/stronger-fewer-superior-harnessing-vision) |余若蒙| 
| 11 | Alpha-CLIP: A CLIP Model Focusing on Wherever You Want | [论文链接](https://arxiv.org/abs/2312.03818) | [代码仓](https://github.com/SunzeY/AlphaCLIP) | [pwc链接](https://paperswithcode.com/paper/alpha-clip-a-clip-model-focusing-on-wherever) |何维刚| 
| 12 | Frequency-Adaptive Dilated Convolution for Semantic Segmentation | [论文链接](https://arxiv.org/abs/2403.05369) | [代码仓](https://github.com/Linwei-Chen/FADC) |  [pwc链接](https://paperswithcode.com/paper/frequency-adaptive-dilated-convolution-for) |吴楷|

#### 【加入社群】
领取任务的同学请加QQ群了解更多信息
QQ群号：885348259（如果群号未能搜索到，请扫下方二维码加群）
![输入图片说明](https://foruda.gitee.com/images/1713587291451580192/22e2e145_10126580.png "YV~~97@RI@BY@_WQ_WE7)%R(1).png")

MindSpore/community

内容风险标识

评论 (32)

MindSpore/community .gitee-modal { width: 500px !important; }

内容风险标识