{"id":19024029,"url":"https://github.com/cvhub520/awesome-computer-vision","last_synced_at":"2026-01-28T13:01:20.780Z","repository":{"id":161930728,"uuid":"612653231","full_name":"CVHub520/awesome-computer-vision","owner":"CVHub520","description":null,"archived":false,"fork":false,"pushed_at":"2023-03-26T16:38:47.000Z","size":30,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-10-19T09:46:50.694Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CVHub520.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-03-11T15:33:04.000Z","updated_at":"2024-05-27T21:34:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"d9921947-e474-4443-9ccc-f9c345617268","html_url":"https://github.com/CVHub520/awesome-computer-vision","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CVHub520/awesome-computer-vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVHub520%2Fawesome-computer-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVHub520%2Fawesome-computer-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVHub520%2Fawesome-computer-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVHub520%2Fawesome-computer-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CVHub520","download_url":"https://codeload.github.com/CVHub520/awesome-computer-vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CVHub520%2Fawesome-computer-vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28845762,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-28T12:37:07.070Z","status":"ssl_error","status_checked_at":"2026-01-28T12:37:06.657Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":"2024-11-08T20:34:29.521Z","updated_at":"2026-01-28T13:01:20.761Z","avatar_url":"https://github.com/CVHub520.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"\n## 关注我们\n\u003cdiv align=center\u003e\n\u003cp\u003e门头沟学院AI视觉实验室御用公众号 | 学术 | 科研 | 就业\u003c/p\u003e\n\u003cp\u003e扫描下方二维码，然后回复关键词“\u003cb\u003e进群\u003c/b\u003e”，即可加入“读者交流群”\u003c/p\u003e\n\u003cimg src=\"https://github.com/CVHuber/awesome-cv/blob/main/640.jfif\" width = \"250\" height = \"270\" alt=\"欢迎大家关注我们的公众号CVHub，每日都给大家带来原创、多领域、有深度的前沿AI论文解读与工业成熟解决方案！\"\u003e\n\u003c/div\u003e\n\n\n\u003cfont size=6\u003e\u003ccenter\u003e\u003cbig\u003e\u003cb\u003e Awesome Computer Vision [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) \u003c/b\u003e\u003c/big\u003e\u003c/center\u003e\u003c/font\u003e\n\nThis is a list of computer vison related resources. \n\nThe timeline follows the time of arxiv.org publication.\n\nPlease feel free to [pull requests](https://github.com/CVHub520/awesome-computer-vision/pulls) or [open an issue](https://github.com/CVHub520/awesome-computer-vision/issues) to add papers.\n\n---\n\n\u003cfont size=5\u003e\u003ccenter\u003e\u003cb\u003e Table of Contents \u003c/b\u003e \u003c/center\u003e\u003c/font\u003e\n- [Awesome Classification](#awesome-classification)\n\n- [Awesome Segmentation](#awesome-segmentation)\n\n- [Awesome Detection](#awesome-detection)\n\n- [Awesome Low Level Vison](#awesome-low-level-vison)\n\n- [Awesome 3D Vision](#awesome-3d-vision)\n    - [Awesome 3D Classification \u0026 Detection \u0026 Segmentation](#awesome-3d-classification--detection--segmentation)\n    - [Awesome 3D Representations](#awesome-3d-representations)\n    - [Awesome 3D Reconstruction](#awesome-3d-reconstruction)\n    - [Awesome Depth \u0026 Flow Estimation](#awesome-depth--flow-estimation)\n    - [Awesome Neural Rendering](#awesome-neural-rendering)\n    - [Awesome SLAM](#awesome-slam)\n- [Awesome Diffusion](#awesome-diffusion)\n\n- [Awesome Network Architectures And Techniques](#awesome-network-architectures-and-techniques)\n\n- [Awesome Optimization Methods](#awesome-optimization-methods)\n\n- [Awesome Face Recognition](#awesome-face-recognition)\n\n# Awesome Classification\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | FSL | ZSL |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Few-shot Learning | Zero-shot Learning |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | FGC |  | - | - | - | - |\n| 任务类型 |  Fine-Grained Classification |    | -| - | -| - |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Medical |-| - | - | - | Other |\n|  其他特性 | Medical Image Classification |  - | -| - | - | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|Shape-Aware Fine-Grained Classification of Erythroid Cells | | __`CNN\u0026Trans`__ __`Sup`__  __`FGC`__   __`Medical`__   |      |[GitHub![](https://img.shields.io/github/stars/wangye8899/bmec?style=social)](https://github.com/wangye8899/bmec) | [BMEC：基于形状感知的红细胞细粒度分类](https://mp.weixin.qq.com/s/zr6ODsmj85JsnQ1Uoq2xdg)  |\n## Blogs \n## Libraies\n\n\n# Awesome Segmentation\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Semantic | Instance | Video | Medical | Aut | Other |\n| 任务类型 | Semantic Segmentation | Instance Segmentation |   Video Segmentation  | Medical Segmentation |  Autonomous Driving Segmentation | Saliency Segmentation... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal | UH-Res | Adv | - | - | Other |\n|  其他特性 | MultiModal Learning |  Ultra-high Resolution | Adversarial Training | - | - | - |\n\n\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|Delivering Arbitrary-Modal Semantic Segmentation | CVPR 2023 | __`CNN\u0026Trans`__ __`Sup`__  __`Semantic`__  __`MultiModal`__  |      |[GitHub![](https://img.shields.io/github/stars/jamycheung/DELIVER?style=social)](https://github.com/jamycheung/DELIVER) | [基于编解码架构的强大语义分割基线，解锁多模态语义分割的正确姿势](https://zhuanlan.zhihu.com/p/613293738)  |\n| ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-high Resolution Segmentation | CVPR 2022 | __`CNN`__ __`Sup`__  __`Semantic`__  __`UH-Res`__ |        | [GitHub![](https://img.shields.io/github/stars/cedricgsh/ISDNet?style=social)](https://github.com/cedricgsh/ISDNet) | [探索超高分辨率图像分割的高效之道](https://zhuanlan.zhihu.com/p/611138087)  |\n| Multi-modal contrastive mutual learning and pseudo-label re-learning for semi-supervised medical image segmentation | MIA 2023  | __`CNN`__ __`Semi`__  __`Medical`__  __`MultiModal`__ |        |- | [用于半监督医学图像分割的多模态对比互学习和伪标签再学习方法](https://mp.weixin.qq.com/s/r_5g9I4MGoydpZ2pOix1sA)  |\n| Class-Aware Adversarial Transformers for Medical Image Segmentation | NeuraIPS 2022  | __`CNN\u0026Trans`__ __`Sup`__  __`Adv`__  |        |- | [最新类别感知对抗Transformer分割网络CASTformer](https://mp.weixin.qq.com/s/qAq54Tg_j9AekmMeMwFnwQ)  |\n| DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation | NeuraIPS 2022  | __`Trans`__ __`Sup`__  __`Medical`__  |        |[GitHub![](https://img.shields.io/github/stars/mindflow-institue/daeformer?style=social)](https://github.com/mindflow-institue/daeformer)  | [DAE-Former：高效双重注意力引导的Transformer网络称霸医学图像分割任务](https://mp.weixin.qq.com/s/RL45_CKwKAwN9hm1t4vUJA)  |\n\n\n\n##  Blogs \n- [语义分割大盘点](http://automl.chalearn.org/)\n- [关于语义分割的亿点思考](https://zhuanlan.zhihu.com/p/595753988)\n\n## Libraies\n- [mmsegmentation](https://github.com/open-mmlab/mmsegmentation)\n- [PaddleSeg](https://github.com/open-mmlab/mmsegmentation)\n\n\n\n# Awesome Detection\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | FSL | ZSL |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Few-shot Learning | Zero-shot Learning |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Small | Moving | Oriented | Body | Head | Other |\n| 任务类型 |  Small Object Detection |  Moving Object Detection  | Oriented Object Detection| Body Detection | Head Detection| License Plate Detection... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | RGB-D | Real-Time | Video | OpenWorld | Aerial | Other |\n|  其他特性 | RGB-D Salient Object Detection |  Real-Time Object Detection | Video Salient Object Detection | Open World Object Detection | Object Detection In Aerial Images | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|Open World DETR: Transformer based Open World Object Detection | CVPR 2022 | __`CNN\u0026Trans`__ __`Sup`__  __`Semi`__   __`OpenWorld`__  |      |[GitHub![](https://img.shields.io/github/stars/akshitac8/OW-DETR?style=social)](https://github.com/akshitac8/OW-DETR) | [基于DETR的开放世界目标检测——从入门到喜欢](https://mp.weixin.qq.com/s/AAqc_XuRS9MTyU4nuO_6qw)  |\n\n## Blogs \n## Libraies\n\n\n# Awesome 3D Classification\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Semantic | Instance | Video | Medical | Aut | Other |\n| 任务类型 | Semantic Segmentation | Instance Segmentation |   Video Segmentation  | Medical Segmentation |  Autonomous Driving Segmentation | Saliency Segmentation... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal | UH-Res | - | - | - | Other |\n|  其他特性 | MultiModal Learning |  Ultra-high Resolution | - | - | - | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n\n## Blogs \n## Libraies\n\n# Awesome 3D Detection\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Semantic | Instance | Video | Medical | Aut | Other |\n| 任务类型 | Semantic Segmentation | Instance Segmentation |   Video Segmentation  | Medical Segmentation |  Autonomous Driving Segmentation | Saliency Segmentation... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal | UH-Res | - | - | - | Other |\n|  其他特性 | MultiModal Learning |  Ultra-high Resolution | - | - | - | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n\n\n## Blogs \n## Libraies\n\n# Awesome 3D Segmentation\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Semantic | Instance | Video | Medical | Aut | Other |\n| 任务类型 | Semantic Segmentation | Instance Segmentation |   Video Segmentation  | Medical Segmentation |  Autonomous Driving Segmentation | Saliency Segmentation... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal | UH-Res | - | - | - | Other |\n|  其他特性 | MultiModal Learning |  Ultra-high Resolution | - | - | - | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|  :fire::fire: UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation | CVPR 2022 | __`CNN\u0026Trans`__ __`Sup`__  __`Semantic`__  __`Medical`__ |        | [GitHub![](https://img.shields.io/github/stars/Amshaker/unetr_plus_plus?style=social)](https://github.com/Amshaker/unetr_plus_plus) | [UNETR++：轻量级的共享权重Transformer称霸医学图像分割领域](https://mp.weixin.qq.com/s/fcF5WibfFADnMI1TLaNPng)  |\n\n## Blogs \n## Libraies\n\n# Awesome Low Level Vison\n## Articles And Interpretation\n## Blogs \n## Libraies\n\n# Awesome 3D Vision\n# Awesome 3D Representations\n## Articles And Interpretation\n## Blogs \n## Libraies\n\n\n# Awesome 3D Reconstruction\n## Articles And Interpretation\n## Blogs \n## Libraies\n\n\n# Awesome Depth \u0026 Flow Estimation\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | FSL | ZSL |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Few-shot Learning | Zero-shot Learning |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Mono | Stereo | Match | Flow |  |  |\n| 任务类型 | Monocular Depth Estimation | Stereo Depth Estimation  |   Stereo Match  | Optical Flow Estimation |    |  |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Night | Rel | Met | Rel\u0026Met | Out | In |\n|  其他特性 | Nighttime |  Relative Depth | Metric Depth | Relative \u0026 Metric Depth |Outdoor Domain | Indoor Domain |\n\n\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|  :fire: ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth | - | __`CNN\u0026Trans`__ __`ZSL`__  __`Mono`__  __`Rel\u0026Met`__ |   NYU REL 0.075   |[GitHub![](https://img.shields.io/github/stars/isl-org/ZoeDepth?style=social)](https://github.com/isl-org/ZoeDepth) | [第一个结合相对和绝对深度的多模态单目深度估计网络](https://zhuanlan.zhihu.com/p/615166220)  |\n| Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation | CVPR 2023 | __`CNN\u0026Trans`__ __`Self`__  __`Mono`__  __`Rel`__  |    KITTI REL 0.102   |[GitHub![](https://img.shields.io/github/stars/noahzn/Lite-Mono?style=social)](https://github.com/noahzn/Lite-Mono) | [一种新的轻量级自监督单目深度估计方法](https://zhuanlan.zhihu.com/p/614680720)  |\n\n\n## Blogs \n## Libraies\n\n\n# Awesome Neural Rendering\n## Articles And Interpretation\n## Blogs \n## Libraies\n\n\n# Awesome SLAM\n## Articles And Interpretation\n## Blogs \n## Libraies\n\n\n# Awesome Diffusion\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | FSL | ZSL |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Few-shot Learning | Zero-shot Learning |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  |  | Lang | T2I | T2V | T23D | I2T |  |\n| 任务类型 | Language | Text-to-Text  |  Text-to-Image    | Text-to-Video  | Text-to-3D  |  Image-to-Text  |  |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal| ImgGen |ImgEdit | ILU |    |    |\n|  其他特性 | MultiModal Learning | Image Generation |Image Editing | Image-and-Language Understanding  |     |  |\n\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n| SINE: SINgle Image Editing with Text-to-Image Diffusion Models | CVPR 2023 | __`GEN`__ __`T2I`__  __`Lang`__ __`ImgEdit`__  |      |[GitHub![](https://img.shields.io/github/stars/zhang-zx/SINE?style=social)](https://github.com/zhang-zx/SINE) | [SINE: 一种基于扩散模型的单图像编辑解决方案](https://mp.weixin.qq.com/s/zZztD_HkXCiCu_3Fc07yTg)  |\n| InstructPix2Pix: Learning to Follow Image Editing Instructions | CVPR 2023 (Highlight) | __`GEN`__ __`T2I`__  __`Lang`__ __`ImgEdit`__  |       |[GitHub![](https://img.shields.io/github/stars/noahzn/Lite-Mono?style=social)](https://github.com/noahzn/Lite-Mono) | [InstructPix2Pix: 一种无需微调新的快速图像编辑方法](https://mp.weixin.qq.com/s/cJtqmpnkSWSMK4BxLLLm7g)  |\n| Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models | CVPR 2023 (Highlight) | __`GEN`__ __`T2I`__  __`Lang`__ __`ImgEdit`__  |       | - | [一文深度剖析扩散模型究竟学到了什么？](https://mp.weixin.qq.com/s/mf-bGv9i7pypHYKbU7U1Ng)  |\n| Image-and-Language Understanding from Pixels Only |  | __`GEN`__ __`I2T`__  __`MultiModal`__ __`ILU`__  |       | - | [CLIPPO：利用Transformer建立多模态模型新范式！](https://mp.weixin.qq.com/s/HZcAMMiiduwxUwaBqjWgCw)  |\n| GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models |  | __`GEN`__ __`T2I`__  __`ImgGen`__ |       | [GitHub![](https://img.shields.io/github/stars/openai/glide-text2im?style=social)](https://github.com/openai/glide-text2im)  | [OpenAI 年度最新力作 GLIDE：新生代文本引导扩散模型](https://mp.weixin.qq.com/s/sDd1A3HBqKgMnrNSooOqcw)  |\n\n## Blogs \n\n## Libraies\n\n\n# Awesome Network Architectures And Techniques\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | NAS | Distill | Pruning | Quant | Transfer | Other |\n| 任务类型 | Neural Architecture Search | Knowledge Distillation |  Network Pruning  | Network Quantization |  Transfer Learning | Reinforcement Learning... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal |  | - | - | - | Other |\n|  其他特性 | MultiModal Learning |   | - | - | - | - |\n\n\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|Rethinking Vision Transformers for MobileNet Size and Speed | NeurIPs 2022 | __`Trans`__ __`Sup`__   |  -   |[GitHub![](https://img.shields.io/github/stars/snap-research/EfficientFormer?style=social)](https://github.com/snap-research/EfficientFormer) | [EfficientFormerV2: Transformer家族中的MobileNet](https://mp.weixin.qq.com/s/CWir9KFQ_W34kJ_bMeY5KQ)  |\n|FlexiViT: One Model for All Patch Sizes |  | __`Trans`__ __`Sup`__   |  -   |[GitHub![](https://img.shields.io/github/stars/google-research/big_vision?style=social)](https://github.com/google-research/big_vision) | [FlexiViT: 谷歌手把手教你如何灵活切片](https://mp.weixin.qq.com/s/melu4UePAq301dZpjxsL2A)  |\n|ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders |  | __`CNN`__ __`Sup`__   |  -   |[GitHub![](https://img.shields.io/github/stars/facebookresearch/ConvNeXt-V2?style=social)](https://github.com/facebookresearch/ConvNeXt-V2) | [ConvNeXt-V2：当 MAE 遇见 ConvNeXt 会碰撞出怎样的火花？](https://mp.weixin.qq.com/s/6msbFRNpsO9BVL7-yi-wYA)  |\n\n## Blogs \n## Libraies\n\n\n# Awesome Optimization Methods\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | Meta | Other |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Meta Learning | Weakly-Supervised... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Loss | Data | - | - | - | Other |\n| 任务类型 | Loss Function  | Data Augmentation |  -  | - |  - | ... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | MultiModal |  | - | - | - | Other |\n|  其他特性 | MultiModal Learning |   | - | - | - | - |\n\n\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|LMFLOSS: A Hybrid Loss For Imbalanced Medical Image Classification |  | __`CNN`__ __`Loss`__   |  -   | | [LMFLOSS：用于解决不平衡医学图像分类的新型混合损失函数](https://mp.weixin.qq.com/s/G8hyI4F-WWpcPG4UYPbfdQ)  |\n\n## Blogs \n## Libraies\n\n# Awesome Face Recognition\n## Articles And Interpretation\n| Type |  简称 |   |   |   |   |   |\n|:---:|:---:|:---:|:---:|:---:|:---:|:---:|\n|  |  |  |  |  | | |\n|  | CNN | Trans | CNN\u0026Trans | RNN | GEN | Other |\n| 网络类型 | CNN | Transformer | CNN + Transformer | RNN |  GAN/Diffusion | GNN... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | Sup | UnSup | Self | Semi | FSL | ZSL |\n| 监督方式 |  Supervised Learning |  Unsupervised Learning | Self-Supervised Learning | Semi-Supervised Learning |  Few-shot Learning | Zero-shot Learning |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | - | - | - | - | - | - |\n| 任务类型 |  - |  -  | -| - | -| -... |\n|  |  |  |  |  | | |\n|  |  |  |  |  | | |\n|  | - | - | - | - | - | - |\n|  其他特性 | - | - | - | - | - | - |\n\n| Paper | Publication | Type | 性能 | 代码 |  解读 | \n| :- | :---| :---:| :---: | :---: |    :---: |     \n|BoundaryFace: A mining framework with noise label self-correction for Face Recognition | ECCV 2022 | __`CNN`__   |      |[GitHub![](https://img.shields.io/github/stars/SWJTU-3DVision/BoundaryFace?style=social)](https://github.com/SWJTU-3DVision/BoundaryFace) | [人脸识别新方法 BoundaryFace：一种基于噪声标签自校正框架(附源码实现)](https://mp.weixin.qq.com/s/U0luh7njdp2e3AjKoNfZbQ)  |\n## Blogs \n## Libraies","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcvhub520%2Fawesome-computer-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcvhub520%2Fawesome-computer-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcvhub520%2Fawesome-computer-vision/lists"}