Duo Li

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

d-li14

PyTorch implementation of EfficientNetV2 family

d-li14

Face Attribute Prediction on CelebA benchmark with PyTorch Implementation

d-li14

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

d-li14

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

d-li14

PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

d-li14

[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

d-li14

[CVPR 2020] Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives

d-li14

PyTorch implementation of Lambda Network and pretrained Lambda-ResNet

d-li14

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2

d-li14