geolocal commited on
Commit
9fbb3e9
1 Parent(s): 9db4045

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -6
README.md CHANGED
@@ -59,15 +59,42 @@ the following use cases are recommended for StreetCLIP.
59
  ## Direct Use
60
 
61
  StreetCLIP can be used out-of-the box using zero-shot learning to infer the geolocation of images on a country, region,
62
- or city level. Given that StreetCLIP was pretrained on a dataset of stree-level urban and rural images,
63
  the best performance can be expected on images from a similar distribution.
64
 
65
- Broader direct use cases
 
66
 
67
  ## Downstream Use
68
 
69
  StreetCLIP can be finetuned for any downstream applications that require geographic or street-level urban or rural
70
- scene understanding.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
  ## Out-of-Scope Use
73
 
@@ -80,9 +107,8 @@ attempting to geolocalize users' private images
80
 
81
  ## Recommendations
82
  We encourage the community to apply StreetCLIP to applications with significant social impact of which there are many.
83
- Examples include analyzing the built environment (i.e. building quality, type, or energy efficiency classification),
84
- infrastructure (i.e. road quality, utility pole maintenance, identifying damage from natural disasters), and natural
85
- environment (i.e. image segmentation, vegetation mapping and classification, tracking deforestation).
86
 
87
  ## How to Get Started with the Model
88
 
 
59
  ## Direct Use
60
 
61
  StreetCLIP can be used out-of-the box using zero-shot learning to infer the geolocation of images on a country, region,
62
+ or city level. Given that StreetCLIP was pretrained on a dataset of street-level urban and rural images,
63
  the best performance can be expected on images from a similar distribution.
64
 
65
+ Broader direct use cases are any zero-shot image classification tasks that rely on urban and rural street-level
66
+ understanding or geographical information relating visual clues to their region of origin.
67
 
68
  ## Downstream Use
69
 
70
  StreetCLIP can be finetuned for any downstream applications that require geographic or street-level urban or rural
71
+ scene understanding. Examples of use cases are the following:
72
+
73
+ **Understanding the Built Environment**
74
+
75
+ - Analyzing building quality
76
+ - Building type classifcation
77
+ - Building energy efficiency Classification
78
+
79
+ **Analyzing Infrastructure**
80
+
81
+ - Analyzing road quality
82
+ - Utility pole maintenance
83
+ - Identifying damage from natural disasters or armed conflicts
84
+
85
+ **Understanding the Natural Environment**
86
+
87
+ - Mapping vegetation
88
+ - Vegetation classification
89
+ - Soil type classifcation
90
+ - Tracking deforestation
91
+
92
+ **General Use Cases**
93
+
94
+ - Street-level image segmentation
95
+ - Urban and rural scene classification
96
+ - Object detection in urban or rural environments
97
+ - Improving navigation and self-driving car technology
98
 
99
  ## Out-of-Scope Use
100
 
 
107
 
108
  ## Recommendations
109
  We encourage the community to apply StreetCLIP to applications with significant social impact of which there are many.
110
+ The first three categories of potential use cases under Downstream Use list potential use cases with social impact
111
+ to explore.
 
112
 
113
  ## How to Get Started with the Model
114