Stefan Riezler, Raphael Schumann
We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| raphael-sch/map2seq_vln | canonical | 3 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| get_config | Ran | raphael-sch/map2seq_vln/vln/utils.py code served (permissive licence) · get_code("6225a0596daf620b") |
| load_datasets | Ran | raphael-sch/map2seq_vln/vln/utils.py code served (permissive licence) · get_code("06e4c15a96bcb6fb") |
| load_features | Ran | raphael-sch/map2seq_vln/vln/env.py code served (permissive licence) · get_code("010f3141fcd0a2a7") |
| get_slices | Not yet run | raphael-sch/map2seq_vln/panorama_preprocessing/fourth_layer/cut_panos.py code served (permissive licence) · get_code("b7135646f83bfb5f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and tries to follow the described route. Most prior work has been conducted in indoor scenarios where best results were obtained for navigation on routes that are similar to the training routes, with sharp drops in performance when testing on unseen environments. We focus on VLN in outdoor scenarios and find that in contrast to indoor VLN, most of the gain in outdoor VLN on unseen data is due to features like junction type embedding or heading delta that are specific to the respective environment graph, while image information plays a very minor role in generalizing VLN to unseen outdoor areas. These findings show a bias to specifics of graph representations of urban environments, demanding that VLN tasks grow in scale and diversity of geographical environments. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.13838")
get_code_for_paper("2203.13838")
have("2203.13838")
Connect an agent — have() is free.