image net a bit of formatting

README.md

@@ -176,16 +176,15 @@ We note that since IDEFICS was trained on PMD (which contains COCO), the evaluat
 |            |      16 |                 57.0 |                 48.4 |                   27.9 |                  42.6 |               67.4 |           99.7 |             89.4 |             64.5 |             - |                     50.9 |                   - |                      67.8 |                              - |
 |            |      32 |                 57.9 |                 49.6 |                   28.3 |                  43.7 |               68.1 |           98.0 |             90.5 |             64.4 |             - |                     49.8 |                   - |                      67.0 |                              - |
 
-For ImageNet-1k, we also report results where the priming samples are selected to be similar (i.e. close in a vector space) to the queried instance.
+For ImageNet-1k, we also report results where the priming samples are selected to be similar (i.e. close in a vector space) to the queried instance. This is the Retrieval-based In-Context Example Selection (RICES in short) approach introduced by [Yang et al. (2021)](https://arxiv.org/abs/2109.05014).
 
-ImageNet-1k Evaluation:
-| Model      |   Shots |   ImageNet-1k |
-|:-----------|--------:|-----------:|
-| IDEFIX 80B |      16, 1k support set |       65.4 |
-|            |      16, RICES 5k support set |       72.9 |
+| Model      |   Shots | Support set size | Shots selection | ImageNet-1k<br>Top-1 acc. |
+|:-----------|--------:|-----------------:|:----------------|--------------------------:|
+| IDEFIX 80B |      16 | 1K               | Random          |                      65.4 |
+|            |      16 | 5K               | RICES           |                      72.9 |
 <br>
-| IDEFIX 9B  |      16, 1k support set |       53.5 |
-|            |      16, RICES 5k support set |       64.5 |
+| IDEFIX 9B  |      16 | 1K               | Random          |                      53.5 |
+|            |      16 | 5K               | RICES           |                      64.5 |
 
 Fairness Evaluations:
 | Model      |   Shots |   FairFaceGender (accuracy) |   FairFaceRace (accuracy) |   FairFaceAge (accuracy) |