epfml / attention-cnn
Source code for "On the Relationship between Self-Attention and Convolutional Layers"
☆1,095Updated 2 years ago
Alternatives and similar repositories for attention-cnn:
Users that are interested in attention-cnn are comparing it to the libraries listed below
- Implementing Attention Augmented Convolutional Networks using Pytorch☆647Updated 3 years ago
- Implementing Stand-Alone Self-Attention in Vision Models using Pytorch☆455Updated 4 years ago
- [arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis☆1,310Updated 4 years ago
- mixup: Beyond Empirical Risk Minimization☆1,171Updated 3 years ago
- list of efficient attention modules☆995Updated 3 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆983Updated 3 months ago
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,195Updated last year
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆787Updated 11 months ago
- Exploring Self-attention for Image Recognition, CVPR2020.☆750Updated 4 years ago
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,534Updated 4 years ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,601Updated 3 years ago
- Codebase for Image Classification Research, written in PyTorch.☆2,147Updated 10 months ago
- My best practice of training large dataset using PyTorch.☆1,092Updated 8 months ago
- Code for Noisy Student Training. https://arxiv.org/abs/1911.04252☆755Updated 3 years ago
- Unsupervised Feature Learning via Non-parametric Instance Discrimination☆750Updated 3 years ago
- A New Optimization Technique for Deep Neural Networks☆535Updated 3 years ago
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,474Updated last year
- An All-MLP solution for Vision, from Google AI☆1,009Updated 4 months ago
- Improving Convolutional Networks via Attention Transfer (ICLR 2017)☆1,450Updated 6 years ago
- PyTorch implementation of Contrastive Learning methods☆1,954Updated last year
- Official Pytorch implementation of CutMix regularizer☆1,226Updated 4 years ago
- PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)☆793Updated 5 years ago
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆591Updated 4 years ago
- Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS☆1,566Updated 7 months ago
- Implementation of Non-local Block.☆1,572Updated last year
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆334Updated 5 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆981Updated 6 months ago
- ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet☆1,171Updated last year
- Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"☆2,100Updated last year
- A memory-efficient implementation of DenseNets☆1,527Updated last year