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
☆80Updated 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
- open source the research work for published on arxiv. https://arxiv.org/abs/2106.02689☆52Updated 3 years ago
- Denoising Masked Autoencoders Help Robust Classification.☆66Updated 2 years ago
- [ICDM 2023] Momentum is All You Need for Data-Driven Adaptive Optimization☆25Updated last year
- Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)☆24Updated last year
- Repository containing code for blockwise SSL training☆29Updated 9 months ago
- Official PyTorch implementation for the paper Minimizing Trajectory Curvature of ODE-based Generative Models, ICML 2023☆85Updated 5 months ago
- ☆25Updated 3 years ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆59Updated last year
- [ICLR 2024] Official code for the paper 'Elucidating the Exposure Bias in Diffusion Models'☆26Updated last year
- This is a offical PyTorch/GPU implementation of SupMAE.☆78Updated 2 years ago
- ☆61Updated 2 years ago
- ☆27Updated 2 years ago
- ☆40Updated 4 months ago
- ☆22Updated 3 years ago
- [NeurIPS 2023] Official Implementation: "Consistent Diffusion Models"☆56Updated 2 years ago
- ResMLP: Feedforward networks for image classification with data-efficient training☆43Updated 4 years ago
- A simple minimal implementation of Reversible Vision Transformers☆125Updated last year
- Hyperbolic Image Segmentation, CVPR 2022☆87Updated 2 years ago
- Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"☆65Updated 2 years ago
- Official code for the paper "Image generation with shortest path diffusion" accepted at ICML 2023.☆23Updated 2 years ago
- [ICLR 2023] Masked Frequency Modeling for Self-Supervised Visual Pre-Training☆76Updated 2 years ago
- Code for "Implicit Normalizing Flows" (ICLR 2021 spotlight)☆36Updated 4 years ago
- Transformers w/o Attention, based fully on MLPs☆93Updated last year
- (Unofficial) PyTorch implementation of the paper Early Convolutions Help Transformers See Better☆43Updated 3 years ago
- Code for "Optimal Transport-Guided Conditional Score-Based Diffusion Model (NeurIPS, 8,7,7,6)"☆63Updated last year
- Visualizing representations with diffusion based conditional generative model.☆95Updated 2 years ago
- [NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"☆72Updated 2 years ago
- Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens☆33Updated 3 months ago
- Unofficial PyTorch implementation of the paper "Generating images with sparse representations"☆38Updated 4 years ago