Srikumar Sastry 4218556acd Add Masked Position Prediction (#260) ...

* Create mp3.py

* Implementation: Position Prediction as an Effective Pretraining Strategy

* Added description for Masked Position Prediction

* MP3 image added

2023-03-07 14:28:40 -08:00

..

ats.png

add adaptive token sampling paper

2021-12-03 19:52:40 -08:00

cait.png

add CaiT, new vision transformer out of facebook AI, complete with layerscale, talking heads, and cls -> patch cross attention

2021-03-31 22:42:16 -07:00

cross_vit.png

add documentation for three recent vision transformer follow-up papers

2021-03-31 09:22:15 -07:00

crossformer2.png

additional diagram

2021-11-22 14:05:39 -08:00

crossformer.png

intent to add

2021-11-22 12:00:03 -08:00

cvt.png

add documentation for three recent vision transformer follow-up papers

2021-03-31 09:22:15 -07:00

dino.png

add image

2021-05-02 15:40:53 -07:00

distill.png

cleanup

2021-03-27 22:14:16 -07:00

esvit.png

add EsViT, by popular request, an alternative to Dino that is compatible with efficient ViTs with accounting for regional self-supervised loss

2022-05-03 10:29:29 -07:00

learnable-memory-vit.png

complete learnable memory ViT, for efficient fine-tuning and potentially plays into continual learning

2022-03-31 09:51:12 -07:00

levit.png

fix images

2021-04-06 13:37:23 -07:00

mae.png

release masked autoencoder

2021-11-12 20:08:48 -08:00

max-vit.png

maxvit intent to build (#211)

2022-04-06 16:12:17 -07:00

mbvit.png

Add files via upload

2021-12-21 20:41:01 +08:00

mp3.png

Add Masked Position Prediction (#260)

2023-03-07 14:28:40 -08:00

nest.png

add NesT

2021-05-27 22:02:17 -07:00

parallel-vit.png

add proposed parallel vit from facebook ai for exploration purposes

2022-03-23 10:42:35 -07:00

patch_merger.png

add patch merger

2022-03-01 16:50:17 -08:00

pit.png

add documentation for three recent vision transformer follow-up papers

2021-03-31 09:22:15 -07:00

regionvit2.png

add RegionViT paper

2021-11-07 09:47:28 -08:00

regionvit.png

add RegionViT paper

2021-11-07 09:47:28 -08:00

scalable-vit-1.png

add scalable vit, from bytedance AI

2022-03-22 17:02:47 -07:00

scalable-vit-2.png

add scalable vit, from bytedance AI

2022-03-22 17:02:47 -07:00

sep-vit.png

intent to build (#210)

2022-03-31 14:30:23 -07:00

simmim.png

add SimMIM

2021-11-21 15:50:19 -08:00

t2t.png

cleanup

2021-03-27 22:14:16 -07:00

twins_svt.png

add Twins SVT (small)

2021-04-29 14:54:06 -07:00

vit_for_small_datasets.png

add ViT for small datasets https://arxiv.org/abs/2112.13492

2021-12-28 10:58:21 -08:00

vit.gif

cleanup

2021-03-27 22:14:16 -07:00

vivit.png

add vivit

2022-10-24 09:34:04 -07:00