[Fix] Fix UniFormer README and metafile

configs/recognition/mvit/README.md

@@ -1,21 +1,14 @@
 # MViT V2
 
-> [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](http://openaccess.thecvf.com//content/CVPR2022/papers/Li_MViTv2_Improved_Multiscale_Vision_Transformers_for_Classification_and_Detection_CVPR_2022_paper.pdf)
+[MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](http://openaccess.thecvf.com//content/CVPR2022/papers/Li_MViTv2_Improved_Multiscale_Vision_Transformers_for_Classification_and_Detection_CVPR_2022_paper.pdf)
 
 <!-- [ALGORITHM] -->
 
 ## Abstract
 
 <!-- [ABSTRACT] -->
 
-In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video
-classification, as well as object detection. We present an improved version of MViT that incorporates
-decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture
-in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where
-it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where
-it outperforms the latter in accuracy/compute. Without bells-and-whistles, MViTv2 has state-of-the-art
-performance in 3 domains: 88.8% accuracy on ImageNet classification, 58.7 boxAP on COCO object detection as
-well as 86.1% on Kinetics-400 video classification.
+In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bells-and-whistles, MViTv2 has state-of-the-art performance in 3 domains: 88.8% accuracy on ImageNet classification, 58.7 boxAP on COCO object detection as well as 86.1% on Kinetics-400 video classification.
 
 <!-- [IMAGE] -->
 

configs/recognition/mvit/metafile.yml

@@ -1,6 +1,6 @@
 Collections:
 - Name: MViT
-  README: configs/recognition/MViT/README.md
+  README: configs/recognition/mvit/README.md
   Paper:
     URL: http://openaccess.thecvf.com//content/CVPR2022/papers/Li_MViTv2_Improved_Multiscale_Vision_Transformers_for_Classification_and_Detection_CVPR_2022_paper.pdf
     Title: "MViTv2: Improved Multiscale Vision Transformers for Classification and Detection"

configs/recognition/uniformerv2/metafile.yml

@@ -8,7 +8,7 @@ Collections:
 Models:
   - Name: uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-B/16
       Batch Size: 32
@@ -30,7 +30,7 @@ Models:
 
   - Name: uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-B/16
       Batch Size: 32
@@ -52,7 +52,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -73,7 +73,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -94,7 +94,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -115,7 +115,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics400-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics400-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14@336
       Pretrained: Kinetics-710
@@ -136,7 +136,7 @@ Models:
 
   - Name: uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics600-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics600-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-B/16
       Pretrained: Kinetics-710
@@ -158,7 +158,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics600-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics600-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -178,7 +178,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics600-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics600-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -198,7 +198,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics600-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics600-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -218,7 +218,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics600-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics600-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14@336
       Pretrained: Kinetics-710
@@ -236,8 +236,8 @@ Models:
         Top 5 Accuracy: 98.5
     Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/kinetics600/uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics600-rgb_20221219-f984f5d2.pth
 
-  - Name: uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb
-    Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb.py
+  - Name: uniformerv2-base-p16-res224_clip-pre_8xb32-u8_kinetics700-rgb
+    Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-pre_8xb32-u8_kinetics700-rgb.py
     In Collection: UniFormer
     Metadata:
       Architecture: UniFormerV2-B/16
@@ -253,7 +253,7 @@ Models:
     - Dataset: Kinetics-700
       Task: Action Recognition
       Metrics:
-        Top 1 Accuracy: 76.3
+        Top 1 Accuracy: 75.9
         Top 5 Accuracy: 92.9
     Training Log: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics700-rgb/uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics700-rgb.log
     Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics700-rgb/uniformerv2-base-p16-res224_clip_8xb32-u8_kinetics700-rgb_20230313-f02e48ad.pth
@@ -275,14 +275,14 @@ Models:
     - Dataset: Kinetics-700
       Task: Action Recognition
       Metrics:
-        Top 1 Accuracy: 75.9
+        Top 1 Accuracy: 76.3
         Top 5 Accuracy: 92.9
     Training Log: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb.log
     Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb/uniformerv2-base-p16-res224_clip-kinetics710-pre_8xb32-u8_kinetics700-rgb_20230313-69070837.pth
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics700-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics700-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -302,7 +302,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics700-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u16_kinetics700-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -322,7 +322,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics700-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u32_kinetics700-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710
@@ -342,7 +342,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics700-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res336_clip-kinetics710-pre_u32_kinetics700-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14@336
       Pretrained: Kinetics-710
@@ -362,7 +362,7 @@ Models:
 
   - Name: uniformerv2-base-p16-res224_clip-pre_u8_kinetics710-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-pre_u8_kinetics710-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-B/16
       Pretrained: CLIP-400M
@@ -374,8 +374,8 @@ Models:
       Code: https://github.com/OpenGVLab/UniFormerV2
     Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/kinetics710/uniformerv2-base-p16-res224_clip-pre_u8_kinetics710-rgb_20221219-77d34f81.pth
 
-  - Name: uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics700-rgb
-    Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-kinetics710-pre_u8_kinetics700-rgb.py
+  - Name: uniformerv2-large-p14-res224_clip-pre_u8_kinetics710-rgb
+    Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res224_clip-pre_u8_kinetics710-rgb.py
     In Collection: UniFormer
     Metadata:
       Architecture: UniFormerV2-L/14
@@ -390,7 +390,7 @@ Models:
 
   - Name: uniformerv2-large-p14-res336_clip-pre_u8_kinetics710-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p14-res336_clip-pre_u8_kinetics710-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14@336
       Pretrained: Kinetics-710
@@ -404,7 +404,7 @@ Models:
 
   - Name: uniformerv2-base-p16-res224_clip-kinetics710-kinetics-k400-pre_16xb32-u8_mitv1-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-base-p16-res224_clip-kinetics710-kinetics-k400-pre_16xb32-u8_mitv1-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-B/16
       Pretrained: Kinetics-710 + Kinetics-400
@@ -426,7 +426,7 @@ Models:
 
   - Name: uniformerv2-large-p16-res224_clip-kinetics710-kinetics-k400-pre_u8_mitv1-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p16-res224_clip-kinetics710-kinetics-k400-pre_u8_mitv1-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14
       Pretrained: Kinetics-710 + Kinetics-400
@@ -446,7 +446,7 @@ Models:
 
   - Name: uniformerv2-large-p16-res336_clip-kinetics710-kinetics-k400-pre_u8_mitv1-rgb
     Config: configs/recognition/uniformerv2/uniformerv2-large-p16-res336_clip-kinetics710-kinetics-k400-pre_u8_mitv1-rgb.py
-    In Collection: UniFormer
+    In Collection: UniFormerV2
     Metadata:
       Architecture: UniFormerV2-L/14@336
       Pretrained: Kinetics-710 + Kinetics-400

model-index.yml

@@ -15,6 +15,11 @@ Import:
 - configs/recognition/trn/metafile.yml
 - configs/recognition/swin/metafile.yml
 - configs/recognition/c2d/metafile.yml
+- configs/recognition/omnisource/metafile.yml
+- configs/recognition/mvit/metafile.yml
+- configs/recognition/uniformer/metafile.yml
+- configs/recognition/uniformerv2/metafile.yml
+- configs/recognition/videomae/metafile.yml
 - configs/detection/slowfast/metafile.yml
 - configs/detection/slowonly/metafile.yml
 - configs/detection/acrn/metafile.yml