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@CV51，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.【基础网络架构】Entropic Score metric: Decoupling Topology and Size in Training-free NAS
-
论文地址：https://arxiv.org//pdf/2310.04179
-
开源代码（即将开源）：NiccoloCavagnero/EntropicScore · GitHub
2.【基础网络架构】TiC: Exploring Vision Transformer in Convolution
-
论文地址：https://arxiv.org//pdf/2310.04134
-
开源代码：GitHub - zs670980918/MSA-Conv: TiC: Exploring Vision Transformer in Convolution
3.【目标检测：伪装目标】Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmark
-
论文地址：https://arxiv.org//pdf/2310.04253
-
开源代码（即将开源）：GitHub - zc199823/BBNet--CoCOD
4.【语义分割】DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions
-
论文地址：https://arxiv.org//pdf/2310.04181
-
工程主页：DiffPrompter: Differentiable Implicit Visual Prompts for Object-Segmentation in Adverse Conditions
-
开源代码：GitHub - DiffPrompter/diff-prompter
5.【医学图像分割：3D】FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
-
论文地址：https://arxiv.org//pdf/2310.03872
-
开源代码：GitHub - IBM/multimodal-3d-image-segmentation: This repository contains the source code of our proposed multimodal image segmentation frameworks. The network architectures and training procedure are provided to reproduce the experimental results in our publications.
6.【超分辨率重建】Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution
-
论文地址：https://arxiv.org//pdf/2310.04180
-
开源代码：GitHub - I2-Multimedia-Lab/DSAT: The code of ' Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution '.
7.【类别增量学习】OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning
-
论文地址：https://arxiv.org//pdf/2310.03848
-
开源代码：GitHub - gawainxu/OpenIncremen
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。
