CVPR2022论文速递（2022.3.11）！共11篇

整理：AI算法与图像处理，分享请注明出处

CVPR2022论文和代码整理：https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo

欢迎关注：

Conditional Prompt Learning for Vision-Language Models

视觉语言模型的条件提示学习

• 论文/Paper：https://arxiv.org/abs/2203.05557

• 代码/Code：https://github.com/KaiyangZhou/CoOp

Representation Compensation Networks for Continual Semantic Segmentation

• 论文/Paper：https://arxiv.org/abs/2203.05402

• 代码/Code：https://github.com/zhangchbin/RCIL

Spatial Commonsense Graph for Object Localisation in Partial Scenes

连续语义分割的表示补偿网络

• 论文/Paper：https://arxiv.org/abs/2203.05380

• 代码/Code：https://fgiuliari.github.io/projects/SpatialCommonsenseGraph/

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

通过 Shuffled Style Assembly 进行域泛化以进行人脸反欺骗

• 论文/Paper：https://arxiv.org/abs/2203.05340

• 代码/Code：

Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects

迭代对应几何：融合区域和深度以实现无纹理对象的高效 3D 跟踪

• 论文/Paper：https://arxiv.org/abs/2203.05334

• 代码/Code：https://github.com/DLR-RM/3DObjectTracking

GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains

GrainSpace：用于细粒度和域自适应识别谷物的大规模数据集

• 论文/Paper：https://arxiv.org/abs/2203.05306

• 代码/Code：https://github.com/hellodfan/GrainSpace

Contrastive Boundary Learning for Point Cloud Segmentation

点云分割的对比边界学习

• 论文/Paper：https://arxiv.org/abs/2203.05272

• 代码/Code：https://github.com/LiyaoTang/contrastBoundary

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

• 论文/Paper：https://arxiv.org/abs/2203.05238

• 代码/Code：https://github.com/xuxw98/BackToReality

Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability

回到现实：带有形状引导标签增强的弱监督 3D 对象检测

• 论文/Paper：https://arxiv.org/abs/2203.05180

• 代码/Code：https://github.com/CVMI-Lab/KDEP

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack

• 论文/Paper：https://arxiv.org/abs/2203.05154

• 代码/Code：https://github.com/liuye6666/adaptive_auto_attack

Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity

通过自适应自动攻击对对抗鲁棒性的实际评估

• 论文/Paper：https://arxiv.org/abs/2203.05151

• 代码/Code：