Zhiqiang Shen
Zhiqiang Shen
MEAL-V2
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
DSOD
DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.
Un-Mix
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning.
FKD
Official code for our ECCV'22 paper "A Fast Knowledge Distillation Framework for Visual Recognition"
CMC_with_Image_Mixture
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Disc...
MSR-VTT-Challenge
Video to Language Challenge (MSR-VTT Challenge 2016)
S2-BNN
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
SReT
Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"