AhmedSSabir commited on
Commit
df315de
·
verified ·
1 Parent(s): c2559ef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -21
README.md CHANGED
@@ -105,27 +105,6 @@ this table.
105
 
106
  The BERT-CNN row above chooses among all nine candidates. The two-candidate setting is shown below.
107
 
108
- Gains over Best Beam, with paired bootstrap 95% intervals over images:
109
-
110
- | Metric | Gain |
111
- | --- | --- |
112
- | CIDEr | **+0.0325 [+0.021, +0.044]** |
113
- | SPICE | +0.0068 [+0.005, +0.009] |
114
- | BERTScore | +0.0007 [+0.0004, +0.0010] |
115
-
116
- Two retrainings with seeds 43 and 44 gave CIDEr 1.1418 and 1.1415. Both are
117
- significantly above Best Beam.
118
-
119
- **Two-candidate setting (first two beams only).** On the same 5,000 images, the retrained
120
- BERT-CNN reaches CIDEr 1.1317 here, close to the paper's reported 1.131, but falls below
121
- Best Beam with nine candidates. This model improves on Best Beam in both settings.
122
-
123
- | Method | CIDEr, 2 candidates | CIDEr, 9 candidates |
124
- | --- | ---: | ---: |
125
- | Best Beam | 1.1150 | 1.1150 |
126
- | Retrained PyTorch BERT-CNN | 1.1317 | 1.0855 |
127
- | **This model** | **1.1383** | **1.1475** |
128
-
129
  **Ablations on the same benchmark (CIDEr):**
130
 
131
  | Variant | CIDEr |
 
105
 
106
  The BERT-CNN row above chooses among all nine candidates. The two-candidate setting is shown below.
107
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
  **Ablations on the same benchmark (CIDEr):**
109
 
110
  | Variant | CIDEr |