CV计算机视觉每日开源代码Paper with code速览-2023.10.19

精华置顶

墙裂推荐!小白如何1个月系统学习CV核心知识:链接

点击@CV计算机视觉,关注更多CV干货

论文已打包,点击进入—>下载界面

点击加入—>CV计算机视觉交流群

1.【目标检测】Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

  • 论文地址:https://arxiv.org//pdf/2310.12152

  • 开源代码(即将开源):https://github.com/MengLcool/RichSem

2.【语义分割】SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment

  • 论文地址:https://arxiv.org//pdf/2310.12031

  • 开源代码:GitHub - wingrune/SegmATRon

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第1张图片

3.【超分辨率重建】Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach

  • 论文地址:https://arxiv.org//pdf/2310.12004

  • 开源代码(即将开源):GitHub - amandaluof/moe_sr

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第2张图片

4.【多模态】DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

  • 论文地址:https://arxiv.org//pdf/2310.12128

  • 工程主页:DiagrammerGPT (2023)

  • 开源代码:GitHub - aszala/DiagrammerGPT: Official code repository for: DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第3张图片

5.【多模态】On the use of Vision-Language models for Visual Sentiment Analysis: a study on CLIP

  • 论文地址:https://arxiv.org//pdf/2310.12062

  • 开源代码(即将开源):cristinabustos16/CLIP-E · GitHub

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第4张图片

6.【多模态】Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

  • 论文地址:https://arxiv.org//pdf/2310.11784

  • 工程主页:Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

  • 代码即将开源

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第5张图片

7.【多模态】GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment

  • 论文地址:https://arxiv.org//pdf/2310.11513

  • 开源代码:GitHub - djghosh13/geneval: GenEval: An object-focused framework for evaluating text-to-image alignment

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第6张图片

8.【图像编辑】Object-aware Inversion and Reassembly for Image Editing

  • 论文地址:https://arxiv.org//pdf/2310.12149

  • 工程主页:OIR

  • 开源代码(即将开源):GitHub - aim-uofa/OIR

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第7张图片

9.【图像修复】A Comparative Study of Image Restoration Networks for General Backbone Network Design

  • 论文地址:https://arxiv.org//pdf/2310.11881

  • 开源代码:GitHub - Andrew0613/X-Restormer: Arxiv:A Comparative Study of Image Restoration Networks for General Backbone Network Design

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第8张图片

10.【类别增量学习】Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation

  • 论文地址:https://arxiv.org//pdf/2310.11482

  • 开源代码:GitHub - IemProg/TTACIL: Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第9张图片

11.【Zero-Shot Learning】ChatGPT-guided Semantics for Zero-shot Learning

  • 论文地址:https://arxiv.org//pdf/2310.11657

  • 开源代码:GitHub - FHShubho/CGS-ZSL: ChatGPT-guided Semantics for Zero-shot Learning

CV计算机视觉每日开源代码Paper with code速览-2023.10.19_第10张图片

论文已打包,点击进入—>下载界面

CV计算机视觉交流群

群内包含目标检测、图像分割、目标跟踪、Transformer、多模态、NeRF、GAN、缺陷检测、显著目标检测、关键点检测、超分辨率重建、SLAM、人脸、OCR、生物医学图像、三维重建、姿态估计、自动驾驶感知、深度估计、视频理解、行为识别、图像去雾、图像去雨、图像修复、图像检索、车道线检测、点云目标检测、点云分割、图像压缩、运动预测、神经网络量化、网络部署等多个领域的大佬,不定期分享技术知识、面试技巧和内推招聘信息

想进群的同学请添加微信号联系管理员:PingShanHai666。添加好友时请备注:学校/公司+研究方向+昵称

推荐阅读:

CV计算机视觉每日开源代码Paper with code速览-2023.10.18

CV计算机视觉每日开源代码Paper with code速览-2023.10.17

CV计算机视觉每日开源代码Paper with code速览-2023.10.16

使用目标之间的先验关系提升目标检测器性能

港科大提出适用于夜间场景语义分割的无监督域自适应新方法

HSN:微调预训练ViT用于目标检测和语义分割,华南理工和阿里巴巴联合提出

EViT:借鉴鹰眼视觉结构,南开大学等提出ViT新骨干架构,在多个任务上涨点

如何优雅地读取网络的中间特征?

你可能感兴趣的:(CV每日paper,with,code,计算机视觉,人工智能,目标检测,图像分割,超分辨率重建,多模态学习)