https://github.com/open-edge-platform/training_extensions
Training data-efficient image transformers & distillation through attention
Papers with Code 아카이브
Efficient ViTs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 82
Increasing the efficiency of ViTs without the modification of the architecture. (i.e., Key & Query Sparsification, Token pruning & merging)
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/pwc-1/Paper-9/tree/main/5/vit_mae
https://github.com/rwightman/pytorch-image-models
Training data-efficient image transformers & distillation through attention
https://github.com/s-chh/patchrot
Training data-efficient image transformers & distillation through attention
https://github.com/sail-sg/dualformer
All Tokens Matter: Token Labeling for Training Better Vision Transformers
https://github.com/shiming-chen/zslvit
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
https://github.com/siyi-wind/tip
MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
https://github.com/skchen1993/TrangFG
Training data-efficient image transformers & distillation through attention
https://github.com/smu-ivpl/DeepfakeDetection
Training data-efficient image transformers & distillation through attention
https://github.com/tanvir-utexas/PaPr
https://github.com/tianhai123/vit-pytorch
Training data-efficient image transformers & distillation through attention
https://github.com/ttt496/vit-pytorch
Training data-efficient image transformers & distillation through attention
https://github.com/vision-sjtu/quadmamba
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
https://github.com/wangyz1608/knowledge-distillation-via-nd
Training data-efficient image transformers & distillation through attention
https://github.com/zhoudaquan/Refiner_ViT
All Tokens Matter: Token Labeling for Training Better Vision Transformers
https://github.com/zhuang-group/lit
https://github.com/zhuhanqing/lightening-transformer
Training data-efficient image transformers & distillation through attention
https://gitlab.com/birder/birder
Training data-efficient image transformers & distillation through attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.