CVPR2023論文最新速遞！含分割/VIT/點云等多個方向
2023 年 2 月 28 日凌晨，CVPR 2023 頂會論文接收結(jié)果出爐！
CVPR 2023 收錄的工作中 " 擴散模型、多模態(tài)、預(yù)訓(xùn)練、MAE " 相關(guān)工作的數(shù)量會顯著增長。
語義分割/Segmentation - 3 篇
Delivering Arbitrary-Modal Semantic Segmentation
論文/Paper: http://arxiv.org/pdf/2303.01480
代碼/Code: None
Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
論文/Paper: http://arxiv.org/pdf/2303.01276
代碼/Code: https://github.com/xiaoyao3302/CCVC
Token Contrast for Weakly-Supervised Semantic Segmentation
論文/Paper: http://arxiv.org/pdf/2303.01267
代碼/Code: https://github.com/rulixiang/toco
超分/Super-Resolution - 1 篇
OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
論文/Paper: http://arxiv.org/pdf/2303.01091
代碼/Code: None
Transformers - - 2 篇
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
論文/Paper: http://arxiv.org/pdf/2303.01112
代碼/Code: None
AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images
論文/Paper: http://arxiv.org/pdf/2303.00865
代碼/Code: None
點云/Point Clouds - 1 篇
Neural Intrinsic Embedding for Non-rigid Point Cloud Matching
論文/Paper: http://arxiv.org/pdf/2303.01038
代碼/Code: None
其他/Other - 8 篇
Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
論文/Paper: http://arxiv.org/pdf/2303.01311
代碼/Code: None
MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
論文/Paper: http://arxiv.org/pdf/2303.01239
代碼/Code: https://github.com/jingjing12110/MixPHM
Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
論文/Paper: http://arxiv.org/pdf/2303.00971
代碼/Code: https://github.com/zhijieshen-bjtu/dopnet
Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
論文/Paper: http://arxiv.org/pdf/2303.00914
代碼/Code: None
Towards Trustable Skin Cancer Diagnosis via Rewriting Model’s Decision
論文/Paper: http://arxiv.org/pdf/2303.00885
代碼/Code: None
Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training
論文/Paper: http://arxiv.org/pdf/2303.00874
代碼/Code: https://github.com/yutinghe-list/gvsl
Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
論文/Paper: http://arxiv.org/pdf/2303.01052
代碼/Code: None文章來源：http://www.zghlxwxcb.cn/news/detail-401245.html
UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
論文/Paper: https://arxiv.org/abs/2303.00938
代碼/Code: None文章來源地址http://www.zghlxwxcb.cn/news/detail-401245.html
下載1：人工資料大禮包
在「阿遠(yuǎn)學(xué)長」公眾號后臺回復(fù)：【1】
即可領(lǐng)取一份人工資料大禮包
包含機器學(xué)習(xí)、深度學(xué)習(xí)書籍pdf
各大人工智能項目實戰(zhàn)、大廠面試寶典等
下載2：人工智能實戰(zhàn)項目
在「阿遠(yuǎn)」公眾號菜單欄點擊：【實戰(zhàn)項目】
即可手把手復(fù)現(xiàn)人工智能實戰(zhàn)項目
到了這里，關(guān)于CVPR2023最新論文 (含語義分割、擴散模型、多模態(tài)、預(yù)訓(xùn)練、MAE等方向)的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
