ziyuwwang / DynaMixer
☆26Updated 2 years ago
Related projects: ⓘ
- [ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wen…☆76Updated 8 months ago
- PyTorch Implementation of "Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model"☆47Updated last year
- [ICLR 2023] Masked Frequency Modeling for Self-Supervised Visual Pre-Training☆66Updated last year
- [ICLR 2023] “ Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Better Representations”, Ziyu Jian…☆23Updated last year
- ☆25Updated last year
- Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers☆26Updated 2 years ago
- [ICDM 2023] Momentum is All You Need for Data-Driven Adaptive Optimization☆22Updated 5 months ago
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆53Updated 10 months ago
- Code for our ICLR'2022 paper "Generalizing Few-Shot NAS with Gradient Matching"☆21Updated last year
- Bag of Instances Aggregation Boosts Self-supervised Distillation (ICLR 2022)☆33Updated 2 years ago
- ☆16Updated last year
- open source the research work for published on arxiv. https://arxiv.org/abs/2106.02689☆52Updated 2 years ago
- Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)☆21Updated 6 months ago
- [CVPR 2023 Highlight] Masked Image Modeling with Local Multi-Scale Reconstruction☆41Updated last year
- Pytorch implementation of Mix-Shifting-MLP (MS-MLP)☆16Updated 2 years ago
- Switchable Online Knowledge Distillation☆16Updated last year
- PyTorch reimplementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".☆36Updated last year
- The official project website of "NORM: Knowledge Distillation via N-to-One Representation Matching" (The paper of NORM is published in IC…☆19Updated last year
- Pytorch implementation of Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation (CVPR'24)☆24Updated 3 months ago
- ☆32Updated 2 years ago
- Denoising Masked Autoencoders Help Robust Classification.☆57Updated last year
- [NeurIPS 2022] code for the paper, SemMAE: Semantic-guided masking for learning masked autoencoders☆32Updated last year
- Official implementation of AdaViT☆48Updated 2 years ago
- ResMLP: Feedforward networks for image classification with data-efficient training☆38Updated 3 years ago
- ☆27Updated 6 months ago
- ☆40Updated last year
- Code implementation for paper "On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals".☆16Updated 2 years ago
- Implementation of HAT https://arxiv.org/pdf/2204.00993☆46Updated 5 months ago
- Official implementation of the paper "Masked Autoencoders are Efficient Class Incremental Learners"☆36Updated 3 months ago
- Official implementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".☆28Updated last year