Ackesnal's repositories
deit
Official DeiT repository
dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
TokenLabeling
Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
EMO
Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
DynamicViT
[NeurIPS 2021] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
TokenReduction
Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT workshop
evit
Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
SegFormer
Official PyTorch implementation of SegFormer
PEFD
[NeurIPS'22] Projector Ensemble Feature Distillation
T2T-ViT
ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Robust-Vision-Transformer
The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)
volo
VOLO: Vision Outlooker for Visual Recognition
releasing-research-code
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
BossNAS
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
CHoiCe-Dataset
A Cursive Handwriting Dataset with 62 classes and 40 photo for each
bottom-up-attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
ICCV19_VQA-CTI
Repo for our ICCV 19 paper: "Compact Trilinear Interaction for Visual Question Answering"