Update README.md
Browse files
README.md
CHANGED
@@ -44,6 +44,19 @@ end_idx = torch.argmax(outputs.end_logits, axis=1)
|
|
44 |
answers = self.processor.tokenizer.decode(input_tokens[start_idx: end_idx+1]).strip()
|
45 |
```
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
## BibTeX entry
|
48 |
|
49 |
```tex
|
|
|
44 |
answers = self.processor.tokenizer.decode(input_tokens[start_idx: end_idx+1]).strip()
|
45 |
```
|
46 |
|
47 |
+
## Model results
|
48 |
+
|
49 |
+
Extended experimentation can be found in Table 2 of [Hierarchical multimodal transformers for Multi-Page DocVQA](https://arxiv.org/pdf/2212.05935.pdf).
|
50 |
+
You can also check the live leaderboard at the [RRC Portal](https://rrc.cvc.uab.es/?ch=17&com=evaluation&task=4).
|
51 |
+
| Model | HF name | ANLS | APPA |
|
52 |
+
|-----------------------------------------------------------------------------------|:--------------------------------------|:-------------:|:---------:|
|
53 |
+
| [Bert-large](https://huggingface.co/rubentito/bert-large-mpdocvqa/tree/main) | rubentito/bert-large-mpdocvqa | 0.4183 | 51.6177 |
|
54 |
+
| [Longformer-base](https://huggingface.co/rubentito/longformer-base-mpdocvqa) | rubentito/longformer-base-mpdocvqa | 0.5287 | 71.1696 |
|
55 |
+
| [BigBird ITC base](https://huggingface.co/rubentito/bigbird-base-itc-mpdocvqa) | rubentito/bigbird-base-itc-mpdocvqa | 0.4929 | 67.5433 |
|
56 |
+
| [**LayoutLMv3 base**](https://huggingface.co/rubentito/layoutlmv3-base-mpdocvqa) | rubentito/layoutlmv3-base-mpdocvqa | 0.4538 | 51.9426 |
|
57 |
+
| [T5 base](https://huggingface.co/rubentito/t5-base-mpdocvqa) | rubentito/t5-base-mpdocvqa | 0.5050 | 0.0000 |
|
58 |
+
| Hi-VT5 | TBA | 0.6201 | 79.23 |
|
59 |
+
|
60 |
## BibTeX entry
|
61 |
|
62 |
```tex
|