Zhiqiang Shen

DSOD. DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.

MEAL-V2. MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

FKD. Official code for our ECCV'22 paper "A Fast Knowledge Distillation Framework for Visual Recognition"

Un-Mix. Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning.

SReT. Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"

S2-BNN. S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

MSR-VTT-Challenge. Video to Language Challenge (MSR-VTT Challenge 2016)

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 Discrimination"

caffe. Caffe fork that supports MIL and MIMLL with ResNet