Kedreamix / MAE-for-CIFAR
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。
☆66Updated last year
Alternatives and similar repositories for MAE-for-CIFAR:
Users that are interested in MAE-for-CIFAR are comparing it to the libraries listed below
- ☆83Updated last year
- GroupMixAttention and GroupMixFormer☆114Updated last year
- PyTorch code and checkpoints release for OFA-KD: https://arxiv.org/abs/2310.19444☆108Updated 9 months ago
- TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition☆170Updated last year
- visualization：filter、feature map、attention map、image-mask、grad-cam、human keypoint、guided-backpro☆106Updated last year
- Official ImageNet Model repository☆241Updated last year
- 🕹️SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy☆292Updated 5 months ago
- CAM', 'ScoreCAM', 'SSCAM', 'ISCAM' 'GradCAM', 'GradCAMpp', 'SmoothGradCAMpp', 'XGradCAM', 'LayerCAM' using by PyTorch.☆71Updated 3 years ago
- Official implement for ICML2023 paper: "A Closer Look at Self-Supervised Lightweight Vision Transformers"☆121Updated last year
- [AAAI 2024] Prompt-based Distribution Alignment for Unsupervised Domain Adaptation☆55Updated 3 months ago
- 'NKD and USKD' (ICCV 2023) and 'ViTKD' (CVPRW 2024)☆221Updated last year
- iFormer: Inception Transformer☆243Updated 2 years ago
- ☆116Updated 11 months ago
- ☆99Updated last year
- The official code of "Rethinking Local Perception in Lightweight Vision Transformer"☆85Updated last year
- The official implementation for DomainDrop (ICCV 2023).☆48Updated last year
- (CVPR2024)RMT: Retentive Networks Meet Vision Transformer☆319Updated 5 months ago
- ☆244Updated last year
- [CVPR 2024] Rewrite the Stars☆339Updated 8 months ago
- TPAMI：Frequency-aware Feature Fusion for Dense Image Prediction☆330Updated 3 weeks ago
- ☆136Updated 10 months ago
- [CVPR 2024] Official PyTorch Code for "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models"☆263Updated 3 weeks ago
- [ICLR 2024] MogaNet: Efficient Multi-order Gated Aggregation Network☆213Updated 10 months ago
- The repository of Expanding Small-Scale Datasets with Guided Imagination (NeurIPS 2023).☆77Updated last year
- [CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"☆518Updated last year
- 可视化神经网络☆40Updated 2 years ago
- Implementation Code for the ICCASSP 2023 paper " Efficient Multi-Scale Attention Module with Cross-Spatial Learning" and is available at:…☆213Updated last month
- ☆33Updated last year
- A Simple but Effective Downsampling Module For Semantic Segmentation☆98Updated last year
- An unofficial implementation for Detecting Camouflaged Object in Frequency Domain, CVPR 2022 in PyTorch.☆72Updated 2 years ago