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
ECCV2022论文和代码整理:https://github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo
标题:Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition
论文:https://arxiv.org/abs/2209.14498
代码:https://github.com/gist-ailab/teaching-where-to-look
深度学习在人脸识别基准测试中取得了优异的性能,但在低分辨率(LR)图像中性能显著下降。我们提出了一种注意力相似性知识提取方法,该方法将作为教师从高分辨率(HR)网络获得的注意力图转换为作为学生的LR网络,以提高LR识别性能。受人类能够基于HR图像中获得的先验知识从LR图像中近似物体区域的启发,我们利用余弦相似性设计了知识提取损失,使学生网络的注意力与教师网络的注意力相似。在各种LR人脸相关基准上的实验证实,所提出的方法总体上改善了LR设置下的识别性能,通过简单地传输构造良好的注意力图,优于最新的结果
Pointly-Supervised Panoptic Segmentation
SUPR: A Sparse Unified Part-Based Human Representation
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers
Does Medical Imaging learn different Convolution Filters?
GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
Learning to forecast vegetation greenness at fine resolution over Africa with ConvLSTMs