siahuat0727 / RePr
My implementation of RePr training scheme in PyTorch. https://arxiv.org/pdf/1811.07275.pdf
☆71Updated 4 years ago
Related projects: ⓘ
- Implementation for <Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition> in ECCV'18.☆103Updated 2 years ago
- ☆134Updated 5 years ago
- Code for our paper "Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitio…☆53Updated 3 years ago
- [ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2☆103Updated 4 years ago
- Data Augmentation for Object Detection via Progressive and Selective Instance-Switching☆77Updated 3 years ago
- ☆111Updated 6 years ago
- four ways to compare the speed of roi pooling in pytorch☆62Updated 6 years ago
- Reimplement DSOD: Learning Deeply Supervised Object Detectors from Scratch.☆70Updated 4 years ago
- ☆68Updated 5 years ago
- Revisiting RCNN: On Awakening the Classification Power of Faster RCNN (ECCV 2018)☆167Updated 4 years ago
- Code and Pretrained model for IGCV3☆190Updated 5 years ago
- Pytorch0.4.1 codes for Lighthead-RCNN☆51Updated 4 years ago
- ☆107Updated this week
- ☆29Updated 5 years ago
- ☆19Updated 4 years ago
- Synchronized Multi-GPU Batch Normalization☆67Updated 6 years ago
- Efficient HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs☆40Updated 5 years ago
- Light-Head R-CNN in PyTorch☆93Updated 5 years ago
- ☆87Updated 6 years ago
- Pytorch implementation of group normalization in https://arxiv.org/abs/1803.08494 (Following the PyTorch Style)☆87Updated 5 years ago
- Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search☆150Updated 3 years ago
- Code for our NeurIPS'19 paper "Learning Deep Bilinear Transformation for Fine-grained Image Representation"☆105Updated 4 years ago
- Code for CVPR2019 paper《Unequal Training for Deep Face Recognition with Long Tailed Noisy Data》☆67Updated 5 years ago
- Code for IJCAI2019 paper☆44Updated 5 years ago
- ☆19Updated 6 years ago
- Model shared. Top1:67.408/Top5:87.258☆48Updated 6 years ago
- ☆230Updated 5 years ago
- Implementation of "Anchor Loss: Modulating loss scale based on prediction difficulty"☆53Updated 3 years ago
- ☆25Updated 5 years ago