JustinLin610 commited on
Commit
99ee4e5
1 Parent(s): cbfc8da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -27
README.md CHANGED
@@ -51,7 +51,7 @@ However, if you are not satisfied with only using the API, feel free to check ou
51
  <br><br>
52
 
53
  ## Results
54
- ### MUGE Text-to-Image Retrieval
55
  <table border="1" width="100%">
56
  <tr align="center">
57
  <th>Setup</th><th colspan="4">Zero-shot</th><th colspan="4">Finetune</th>
@@ -59,20 +59,20 @@ However, if you are not satisfied with only using the API, feel free to check ou
59
  <tr align="center">
60
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td>
61
  </tr>
62
- <tr align="center">
63
- <td>Wukong<sub>ViT-B</sub></td><td>33.4</td><td>59.3</td><td>69.7</td><td>54.1</td><td>39.2</td><td>66.9</td><td>77.4</td><td>61.2</td>
64
- </tr>
65
  <tr align="center">
66
- <td>R2D2<sub>ViT-B</sub></td><td>-</td><td>-</td><td>-</td><td>-</td><td>47.4</td><td>75.1</td><td>83.5</td><td>68.7</td>
67
- </tr>
68
  <tr align="center">
69
- <td>CN-CLIP<sub>ViT-B</sub></td><td><b>52.1</b></td><td><b>76.7</b></td><td><b>84.4</b></td><td><b>71.1</b></td><td><b>58.4</b></td><td><b>83.6</b></td><td><b>90.0</b></td><td><b>77.4</b></td>
70
- </tr>
 
 
 
71
  </table>
 
72
 
73
-
74
- ### Flickr30K-CN Retrieval
75
- <table border="1" width="100%">
76
  <tr align="center">
77
  <th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
78
  </tr>
@@ -82,19 +82,19 @@ However, if you are not satisfied with only using the API, feel free to check ou
82
  <tr align="center">
83
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
84
  </tr>
85
- <tr align="center">
86
- <td>Wukong<sub>ViT-B</sub></td><td>45.7</td><td>73.8</td><td>82.2</td><td>67.6</td><td>89.6</td><td>94.2</td><td>66.2</td><td>88.7</td><td>94.3</td><td>83.9</td><td>97.6</td><td>99.0</td>
87
- </tr>
88
  <tr align="center">
89
- <td>R2D2<sub>ViT-B</sub></td><td>-</td><td>-</td><td>-</td><td>78.3</td><td>94.6</td><td>97.0</td><td>-</td><td>-</td><td>-</td><td>92.6</td><td><b>99.1</b></td><td><b>99.8</b></td>
90
- </tr>
 
 
 
91
  <tr align="center">
92
- <td>CN-CLIP<sub>ViT-B</sub></td><td><b>62.7</b></td><td><b>86.9</b></td><td><b>92.8</b></td><td><b>79.1</b></td><td><b>94.8</b></td><td><b>97.4</b></td><td><b>74.6</b></td><td><b>93.5</b></td><td><b>97.1</b></td><td><b>93.5</b></td><td>99.0</td><td>99.5</td>
93
- </tr>
94
  </table>
 
95
 
96
-
97
- ### COCO-CN Retrieval
98
  <table border="1" width="100%">
99
  <tr align="center">
100
  <th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
@@ -105,18 +105,41 @@ However, if you are not satisfied with only using the API, feel free to check ou
105
  <tr align="center">
106
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
107
  </tr>
108
- <tr align="center">
109
- <td>Wukong<sub>ViT-B</sub></td><td>49.2</td><td>79.4</td><td>87.9</td><td>67.0</td><td>91.4</td><td>96.7</td><td>48.3</td><td>77.8</td><td>88.8</td><td>65.8</td><td>90.3</td><td>96.6</td>
110
- </tr>
111
  <tr align="center">
112
- <td>R2D2<sub>ViT-B</sub></td><td>-</td><td>-</td><td>-</td><td>75.1</td><td>94.2</td><td>98.1</td><td>-</td><td>-</td><td>-</td><td>76.1</td><td>95.3</td><td>98.5</td>
113
- </tr>
114
  <tr align="center">
115
- <td>CN-CLIP<sub>ViT-B</sub></td><td><b>62.2</b></td><td><b>86.6</b></td><td><b>94.9</b></td><td><b>77.0</b></td><td><b>97.1</b></td><td><b>99.0</b></td><td><b>57.0</b></td><td><b>84.1</b></td><td><b>93.6</b></td><td><b>77.4</b></td><td><b>96.2</b></td><td><b>98.9</b></td>
116
- </tr>
 
 
 
117
  </table>
118
  <br>
119
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
120
  ## Citation
121
  If you find Chinese CLIP helpful, feel free to cite our paper. Thanks for your support!
122
 
 
51
  <br><br>
52
 
53
  ## Results
54
+ **MUGE Text-to-Image Retrieval**:
55
  <table border="1" width="100%">
56
  <tr align="center">
57
  <th>Setup</th><th colspan="4">Zero-shot</th><th colspan="4">Finetune</th>
 
59
  <tr align="center">
60
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td><td>R@1</td><td>R@5</td><td>R@10</td><td>MR</td>
61
  </tr>
 
 
 
62
  <tr align="center">
63
+ <td width="120%">Wukong</td><td>42.7</td><td>69.0</td><td>78.0</td><td>63.2</td><td>52.7</td><td>77.9</td><td>85.6</td><td>72.1</td>
64
+ </tr>
65
  <tr align="center">
66
+ <td width="120%">R2D2</td><td>49.5</td><td>75.7</td><td>83.2</td><td>69.5</td><td>60.1</td><td>82.9</td><td>89.4</td><td>77.5</td>
67
+ </tr>
68
+ <tr align="center">
69
+ <td width="120%">CN-CLIP</td><td>63.0</td><td>84.1</td><td>89.2</td><td>78.8</td><td>68.9</td><td>88.7</td><td>93.1</td><td>83.6</td>
70
+ </tr>
71
  </table>
72
+ <br>
73
 
74
+ **Flickr30K-CN Retrieval**:
75
+ <table border="1" width="120%">
 
76
  <tr align="center">
77
  <th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
78
  </tr>
 
82
  <tr align="center">
83
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
84
  </tr>
 
 
 
85
  <tr align="center">
86
+ <td width="120%">Wukong</td><td>51.7</td><td>78.9</td><td>86.3</td><td>77.4</td><td>94.5</td><td>97.0</td><td>76.1</td><td>94.8</td><td>97.5</td><td>92.7</td><td>99.1</td><td>99.6</td>
87
+ </tr>
88
+ <tr align="center">
89
+ <td width="120%">R2D2</td><td>60.9</td><td>86.8</td><td>92.7</td><td>84.4</td><td>96.7</td><td>98.4</td><td>77.6</td><td>96.7</td><td>98.9</td><td>95.6</td><td>99.8</td><td>100.0</td>
90
+ </tr>
91
  <tr align="center">
92
+ <td width="120%">CN-CLIP</td><td>71.2</td><td>91.4</td><td>95.5</td><td>83.8</td><td>96.9</td><td>98.6</td><td>81.6</td><td>97.5</td><td>98.8</td><td>95.3</td><td>99.7</td><td>100.0</td>
93
+ </tr>
94
  </table>
95
+ <br>
96
 
97
+ **COCO-CN Retrieval**:
 
98
  <table border="1" width="100%">
99
  <tr align="center">
100
  <th>Task</th><th colspan="6">Text-to-Image</th><th colspan="6">Image-to-Text</th>
 
105
  <tr align="center">
106
  <td>Metric</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td><td>R@1</td><td>R@5</td><td>R@10</td>
107
  </tr>
 
 
 
108
  <tr align="center">
109
+ <td width="120%">Wukong</td><td>53.4</td><td>80.2</td><td>90.1</td><td>74.0</td><td>94.4</td><td>98.1</td><td>55.2</td><td>81.0</td><td>90.6</td><td>73.3</td><td>94.0</td><td>98.0</td>
110
+ </tr>
111
  <tr align="center">
112
+ <td width="120%">R2D2</td><td>56.4</td><td>85.0</td><td>93.1</td><td>79.1</td><td>96.5</td><td>98.9</td><td>63.3</td><td>89.3</td><td>95.7</td><td>79.3</td><td>97.1</td><td>98.7</td>
113
+ </tr>
114
+ <tr align="center">
115
+ <td width="120%">CN-CLIP</td><td>69.2</td><td>89.9</td><td>96.1</td><td>81.5</td><td>96.9</td><td>99.1</td><td>63.0</td><td>86.6</td><td>92.9</td><td>83.5</td><td>97.3</td><td>99.2</td>
116
+ </tr>
117
  </table>
118
  <br>
119
 
120
+ **Zero-shot Image Classification**:
121
+ <table border="1" width="100%">
122
+ <tr align="center">
123
+ <th>Task</th><th>CIFAR10</th><th>CIFAR100</th><th>DTD</th><th>EuroSAT</th><th>FER</th><th>FGVC</th><th>KITTI</th><th>MNIST</th><th>PC</th><th>VOC</th>
124
+ </tr>
125
+ <tr align="center">
126
+ <td width="150%">GIT</td><td>88.5</td><td>61.1</td><td>42.9</td><td>43.4</td><td>41.4</td><td>6.7</td><td>22.1</td><td>68.9</td><td>50.0</td><td>80.2</td>
127
+ </tr>
128
+ <tr align="center">
129
+ <td width="150%">ALIGN</td><td>94.9</td><td>76.8</td><td>66.1</td><td>52.1</td><td>50.8</td><td>25.0</td><td>41.2</td><td>74.0</td><td>55.2</td><td>83.0</td>
130
+ </tr>
131
+ <tr align="center">
132
+ <td width="150%">CLIP</td><td>94.9</td><td>77.0</td><td>56.0</td><td>63.0</td><td>48.3</td><td>33.3</td><td>11.5</td><td>79.0</td><td>62.3</td><td>84.0</td>
133
+ </tr>
134
+ <tr align="center">
135
+ <td width="150%">Wukong</td><td>95.4</td><td>77.1</td><td>40.9</td><td>50.3</td><td>-</td><td>-</td><td>-</td><td>-</td><td>-</td><td>-</td>
136
+ </tr>
137
+ <tr align="center">
138
+ <td width="150%">CN-CLIP</td><td>96.0</td><td>79.7</td><td>51.2</td><td>52.0</td><td>55.1</td><td>26.2</td><td>49.9</td><td>79.4</td><td>63.5</td><td>84.9</td>
139
+ </tr>
140
+ </table>
141
+ <br><br>
142
+
143
  ## Citation
144
  If you find Chinese CLIP helpful, feel free to cite our paper. Thanks for your support!
145