整理:AI算法与图像处理
CVPR2022论文和代码整理:https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo
On the Importance of Asymmetry for Siamese Representation Learning
Marginal Contrastive Correspondence for Guided Image Generation
DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow
CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression
Perception Prioritized Training of Diffusion Models
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature
LASER: LAtent SpacE Rendering for 2D Visual Localization
TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
Learning to Deblur using Light Field Generated and Real Defocus Images
Investigating Top-k White-Box and Transferable Black-box Attack
Efficient Maximal Coding Rate Reduction by Variational Forms