Update result table
Browse files
README.md
CHANGED
@@ -171,39 +171,19 @@ We perform checkpoint selection based on validation sets of TODO, and select the
|
|
171 |
|
172 |
TODO: beautiful plots of shots scaling laws.
|
173 |
|
174 |
-
|
|
175 |
-
|
176 |
-
|
|
177 |
-
|
|
178 |
-
|
|
179 |
-
|
|
180 |
-
|
|
181 |
-
|
182 |
-
|
|
183 |
-
|
|
184 |
-
|
|
185 |
-
|
|
186 |
-
|
|
187 |
-
| ScienceQA (accuracy) | 68.9% | 66.3% | - | - | - |
|
188 |
-
| RenderedSST2 | 60.5% | 63.9% | 64.3% | 66.9% | 68.0% |
|
189 |
-
|
190 |
-
|
191 |
-
| 9B IDEFIX | 0-shots | 4-shots | 8-shots | 16-shots | 32-shots |
|
192 |
-
|:-----------------------|:----------|:----------|:----------|:-----------|:-----------|
|
193 |
-
| VQAv2 | 50.9% | 55.6% | 56.4% | 57.2% | 57.9% |
|
194 |
-
| OKVQA | 38.4% | 45.8% | 47.3% | 49.0% | 50.4% |
|
195 |
-
| TextVQA | 25.9% | 26.8% | 26.8% | 28.1% | 28.2% |
|
196 |
-
| TextCaps | 25.4% | 60.9% | 63.7% | 68.0% | 69.7% |
|
197 |
-
| Coco | 46.0% | 88.9% | 96.9% | 99.6% | 101.5% |
|
198 |
-
| NoCaps | 36.8% | 78.5% | 84.3% | 87.2% | 88.6% |
|
199 |
-
| Flickr | 27.3% | 52.2% | 60.3% | 65.0% | 66.0% |
|
200 |
-
| ImageNet1k | 70.7% | | | | |
|
201 |
-
| VizWiz | 35.5% | 42.0% | 42.8% | 45.0% | 45.9% |
|
202 |
-
| VisDial (NDCG) | 48.7% | 48.1% | 47.5% | | |
|
203 |
-
| HatefulMemes (ROC AUC) | 51.7% | 52.6% | 52.3% | 52.5% | 53.1% |
|
204 |
-
| ScienceQA (accuracy) | 44.2% | 41.6% | - | - | - |
|
205 |
-
| RenderedSST2 | 61.8% | 60.6% | 66.8% | 66.0% | 63.4% |
|
206 |
-
|
207 |
|
208 |
# Technical Specifications
|
209 |
|
|
|
171 |
|
172 |
TODO: beautiful plots of shots scaling laws.
|
173 |
|
174 |
+
| Model | Shots | VQAv2 (open-ended vqa acc) | OKVQA (open-ended vqa acc) | TextVQA (open-ended vqa acc) | VizWiz (open-ended vqa acc) | TextCaps (CIDEr) | Coco (CIDEr) | NoCaps (CIDEr) | Flickr (CIDEr) | ImageNet1k (accuracy) | VisDial (NDCG) | HatefulMemes (ROC AUC) | ScienceQA (accuracy) | RenderedSST2 (accuracy) | Winoground (group_score (image_score/text_score)) |
|
175 |
+
|:-----------|--------:|-----------------------------:|-----------------------------:|-------------------------------:|------------------------------:|-------------------:|---------------:|-----------------:|-----------------:|------------------------:|-----------------:|-------------------------:|-----------------------:|--------------------------:|----------------------------------------------------:|
|
176 |
+
| IDEFIX 80B | 0 | 60.1 | 45.2 | 31 | 36 | 56.9 | 91.9 | 65 | 53.7 | 74.3 | 48.9 | 60.7 | 69 | 60.6 | 8 (0.1875/0.225) |
|
177 |
+
| | 4 | 63.5 | 52.4 | 34.7 | 45.9 | 77.9 | 109.3 | 101.1 | 69 | - | 48.7 | 58.7 | 66.3 | 64 | - |
|
178 |
+
| | 8 | 64.6 | 55.3 | 35.5 | 49.3 | 82.6 | 114 | 104.8 | 74.4 | - | 48.2 | 57.9 | - | 64.3 | - |
|
179 |
+
| | 16 | 65.4 | 56.9 | 36.4 | 51.6 | 85.2 | 116.6 | 105.7 | 76.9 | - | - | 56.1 | - | 66.9 | - |
|
180 |
+
| | 32 | 66 | 58.1 | 37 | 52.6 | 86.1 | 116.5 | 106.4 | 79 | - | - | 54.4 | - | 68.1 | - |
|
181 |
+
<br>
|
182 |
+
| IDEFIX 9B | 0 | 50.9 | 38.5 | 25.9 | 35.6 | 25.4 | 46.1 | 36.9 | 27.3 | 70.7 | 48.8 | 51.8 | 44.3 | 61.9 | 5 (16.75/20.75)|
|
183 |
+
| | 4 | 55.6 | 45.9 | 26.8 | 42 | 60.9 | 89 | 78.5 | 52.3 | - | 48.2 | 52.6 | 41.7 | 60.6 | - |
|
184 |
+
| | 8 | 56.5 | 47.4 | 26.9 | 42.9 | 63.8 | 97 | 84.4 | 60.3 | - | 47.5 | 52.3 | - | 66.8 | - |
|
185 |
+
| | 16 | 57.2 | 49.1 | 28.1 | 45 | 68.1 | 99.6 | 87.2 | 65 | - | - | 52.6 | - | 66 | - |
|
186 |
+
| | 32 | 58 | 50.5 | 28.2 | 46 | 69.7 | 101.5 | 88.7 | 66 | - | - | 53.1 | - | 63.5 | - |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
187 |
|
188 |
# Technical Specifications
|
189 |
|