VITA-Group / ViT-Anti-OversmoothingLinks
[ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang
☆81Updated last year
Alternatives and similar repositories for ViT-Anti-Oversmoothing
Users that are interested in ViT-Anti-Oversmoothing are comparing it to the libraries listed below
Sorting:
- PyTorch Implementation of "Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model"☆49Updated 2 years ago
- Denoising Masked Autoencoders Help Robust Classification.☆67Updated 2 years ago
- open source the research work for published on arxiv. https://arxiv.org/abs/2106.02689☆51Updated 3 years ago
- ☆27Updated 3 years ago
- A collection of differentiable SVD methods and ICCV21 "Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance P…☆78Updated last year
- Log-Polar Space Convolution for Convolutional Neural Networks☆12Updated 2 years ago
- [ICLR 2023] Masked Frequency Modeling for Self-Supervised Visual Pre-Training☆78Updated 2 years ago
- This is a offical PyTorch/GPU implementation of SupMAE.☆78Updated 3 years ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆61Updated last year
- [ICDM 2023] Momentum is All You Need for Data-Driven Adaptive Optimization☆27Updated last year
- Implementation of HAT https://arxiv.org/pdf/2204.00993☆51Updated last year
- ☆45Updated 2 years ago
- ☆63Updated 2 years ago
- A simple minimal implementation of Reversible Vision Transformers☆125Updated last year
- Official PyTorch Implementation☆18Updated 2 years ago
- [NeurIPS 2023] Official Implementation: "Consistent Diffusion Models"☆57Updated 2 years ago
- Official code for the paper "Image generation with shortest path diffusion" accepted at ICML 2023.☆23Updated 2 years ago
- Repo for the paper "Extrapolating from a Single Image to a Thousand Classes using Distillation"☆37Updated last year
- Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)☆26Updated last year
- Visualizing representations with diffusion based conditional generative model.☆100Updated 2 years ago
- A torch-based implementation of K-Means and K-Means++☆17Updated 4 years ago
- Official implementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".☆36Updated 2 years ago
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆68Updated last year
- The official github repo for "Test-Time Training with Masked Autoencoders"☆87Updated last year
- Official PyTorch implementation for the paper Minimizing Trajectory Curvature of ODE-based Generative Models, ICML 2023☆88Updated 7 months ago
- Repository containing code for blockwise SSL training