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。
☆58Updated last year
Related projects ⓘ
Alternatives and complementary repositories for MAE-for-CIFAR
- ☆80Updated last year
- Official implement for ICML2023 paper: "A Closer Look at Self-Supervised Lightweight Vision Transformers"☆115Updated last year
- GroupMixAttention and GroupMixFormer☆113Updated 11 months ago
- Official ImageNet Model repository☆220Updated last year
- [CVPR 2024] Rewrite the Stars☆287Updated 6 months ago
- iFormer: Inception Transformer☆243Updated last year
- TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition☆160Updated 11 months ago
- visualization:filter、feature map、attention map、image-mask、grad-cam、human keypoint、guided-backpro☆94Updated last year
- 🕹️SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy☆277Updated 3 months ago
- CMT Pytorch implementation of our CVPR 2022 paper CMT: Convolutional Neural Networks Meet Vision Transformers (https://arxiv.org/pdf/2107…☆93Updated 2 years ago
- PyTorch code and checkpoints release for OFA-KD: https://arxiv.org/abs/2310.19444☆97Updated 7 months ago
- The official code of "Rethinking Local Perception in Lightweight Vision Transformer"☆84Updated last year
- ☆129Updated 8 months ago
- (CVPR2024)RMT: Retentive Networks Meet Vision Transformer☆293Updated 3 months ago
- Scattering Vision Transformer☆50Updated 8 months ago
- CAM', 'ScoreCAM', 'SSCAM', 'ISCAM' 'GradCAM', 'GradCAMpp', 'SmoothGradCAMpp', 'XGradCAM', 'LayerCAM' using by PyTorch.☆69Updated 3 years ago
- [NeurIPS 2022] Implementation of "AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition"☆329Updated 2 years ago
- Implementation Code for the ICCASSP 2023 paper " Efficient Multi-Scale Attention Module with Cross-Spatial Learning" and is available at:…☆196Updated 6 months ago
- A Simple but Effective Downsampling Module For Semantic Segmentation☆81Updated last year
- 'NKD and USKD' (ICCV 2023) and 'ViTKD' (CVPRW 2024)☆217Updated last year
- [ICLR 2024] MogaNet: Efficient Multi-order Gated Aggregation Network☆206Updated 8 months ago
- Wavelet Convolutions for Large Receptive Fields. ECCV 2024.☆291Updated 2 weeks ago
- ☆128Updated 4 months ago
- ☆55Updated 4 months ago
- ☆111Updated 9 months ago
- This is an official implementation for "Scale-Aware Modulation Meet Transformer".☆193Updated last year
- ☆82Updated last year
- Pytorch implementation of Swin MAE https://arxiv.org/abs/2212.13805☆72Updated last year
- [ECCV 2022] Implementation of the paper "Locality Guidance for Improving Vision Transformers on Tiny Datasets"☆77Updated 2 years ago
- Code Implementation of EfficientVMamba☆184Updated 7 months ago