Kedreamix / MAE-for-CIFARLinks
MAE for CIFAR，由于可用资源有限，我们仅在 cifar10 上测试模型。我们主要想重现这样的结果：使用 MAE 预训练 ViT 可以比直接使用标签进行监督学习训练获得更好的结果。这应该是自我监督学习比监督学习更有效的数据的证据。
☆77Updated 2 years ago
Alternatives and similar repositories for MAE-for-CIFAR
Users that are interested in MAE-for-CIFAR are comparing it to the libraries listed below
Sorting:
- visualization：filter、feature map、attention map、image-mask、grad-cam、human keypoint、guided-backpro☆126Updated 2 years ago
- Pytorch ViT for Image classification on the CIFAR10 dataset☆44Updated 3 years ago
- CAM', 'ScoreCAM', 'SSCAM', 'ISCAM' 'GradCAM', 'GradCAMpp', 'SmoothGradCAMpp', 'XGradCAM', 'LayerCAM' using by PyTorch.☆73Updated 3 years ago
- PyTorch code and checkpoints release for OFA-KD: https://arxiv.org/abs/2310.19444☆129Updated last year
- Official implement for ICML2023 paper: "A Closer Look at Self-Supervised Lightweight Vision Transformers"☆136Updated 5 months ago
- 'NKD and USKD' (ICCV 2023) and 'ViTKD' (CVPRW 2024)☆235Updated last year
- GroupMixAttention and GroupMixFormer☆117Updated last year
- Official ImageNet Model repository☆253Updated 2 years ago
- Awesome Fine-grained Visual Classification☆236Updated last year
- 这里陈列了我编写的一些关于深度学习的画图工具，如果觉得有帮助可以给个star.☆41Updated 2 years ago
- The official implementation of [CVPR 2025] "5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks".☆346Updated last month
- 可视化特征图教程☆74Updated 3 years ago
- The official code for our TIP paper 'LayerCAM: Exploring Hierarchical Class Activation Maps for Localization'☆126Updated 3 years ago
- [TNNLS 2025] TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition☆211Updated last month
- ☆85Updated last year
- ImageNet-1K data download, processing for using as a dataset☆104Updated 2 years ago
- Official code for Scale Decoupled Distillation☆41Updated last year
- 这是一个clip-pytorch的模型，可以训练自己的数据集。☆237Updated 2 years ago
- Official implementation of CrossViT. https://arxiv.org/abs/2103.14899☆399Updated 3 years ago
- 可视化神经网络☆38Updated 3 years ago
- [CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels☆315Updated last month
- Codes for ECCV2022 paper - contrastive deep supervision☆68Updated 2 years ago
- [CVPR 2024] Official PyTorch Code for "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models"☆321Updated last week
- Masked Autoencoder meets GANs☆27Updated last year
- ☆250Updated last year
- 博客论文列表：分系列整理☆387Updated last year
- [TNNLS] A Comprehensive Survey of Awesome Visual Transformer Literatures.☆263Updated 2 years ago
- [ICCV2023] This is an official implementation for "Scale-Aware Modulation Meet Transformer".☆210Updated 2 years ago
- 论文 · 撰写 · 排版 · 画图☆33Updated 3 weeks ago
- ☆230Updated 4 months ago