CVPR2023最新论文 (含语义分割、扩散模型、多模态、预训练、MAE等方向)

发布时间：2023-04-20 文章分类：电脑百科 投稿人：赵颖 字号： 默认 | 大 | 超大 打印

CVPR2023论文最新速递！含分割/VIT/点云等多个方向

2023 年 2 月 28 日凌晨，CVPR 2023 顶会论文接收结果出炉！

CVPR 2023 收录的工作中 " 扩散模型、多模态、预训练、MAE " 相关工作的数量会显著增长。
CVPR2023最新论文 (含语义分割、扩散模型、多模态、预训练、MAE等方向)

语义分割/Segmentation - 3 篇

Delivering Arbitrary-Modal Semantic Segmentation

论文/Paper: http://arxiv.org/pdf/2303.01480
代码/Code: None

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

论文/Paper: http://arxiv.org/pdf/2303.01276
代码/Code: https://github.com/xiaoyao3302/CCVC

Token Contrast for Weakly-Supervised Semantic Segmentation

论文/Paper: http://arxiv.org/pdf/2303.01267
代码/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

论文/Paper: http://arxiv.org/pdf/2303.01091
代码/Code: None

Transformers - - 2 篇

Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves

论文/Paper: http://arxiv.org/pdf/2303.01112
代码/Code: None

AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images

论文/Paper: http://arxiv.org/pdf/2303.00865
代码/Code: None

点云/Point Clouds - 1 篇

Neural Intrinsic Embedding for Non-rigid Point Cloud Matching

论文/Paper: http://arxiv.org/pdf/2303.01038
代码/Code: None

其他/Other - 8 篇

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

论文/Paper: http://arxiv.org/pdf/2303.01311
代码/Code: None

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

论文/Paper: http://arxiv.org/pdf/2303.01239
代码/Code: https://github.com/jingjing12110/MixPHM

Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness

论文/Paper: http://arxiv.org/pdf/2303.00971
代码/Code: https://github.com/zhijieshen-bjtu/dopnet

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

论文/Paper: http://arxiv.org/pdf/2303.00914
代码/Code: None

Towards Trustable Skin Cancer Diagnosis via Rewriting Model’s Decision

论文/Paper: http://arxiv.org/pdf/2303.00885
代码/Code: None

Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training

论文/Paper: http://arxiv.org/pdf/2303.00874
代码/Code: https://github.com/yutinghe-list/gvsl

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression

论文/Paper: http://arxiv.org/pdf/2303.01052
代码/Code: None

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

论文/Paper: https://arxiv.org/abs/2303.00938
代码/Code: None


下载1：人工资料大礼包
在「阿远学长」公众号后台回复：【1】
 即可领取一份人工资料大礼包
 包含机器学习、深度学习书籍pdf
 各大人工智能项目实战、大厂面试宝典等
下载2：人工智能实战项目
在「阿远」公众号菜单栏点击：【实战项目】
即可手把手复现人工智能实战项目
标签 , ,