We lifted 8 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| eify/clip_benchmark | pwc_unofficial | 1 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| get_dataset_default_task | Ran | eify/clip_benchmark/clip_benchmark/datasets/builder.py code served (permissive licence) · get_code("dbc602d6bfc435f3") |
| PIL_to_bytes | Not yet run | eify/clip_benchmark/clip_benchmark/webdataset_builder.py code served (permissive licence) · get_code("27180e9964b8cac8") |
| build_dataset | Not yet run | eify/clip_benchmark/clip_benchmark/datasets/builder.py code served (permissive licence) · get_code("63b80a251f3277e4") |
| get_metadata | Not yet run | eify/clip_benchmark/clip_benchmark/datasets/objectnet.py code served (permissive licence) · get_code("f4eee6ad42516616") |
| get_model_collection_from_file | Not yet run | eify/clip_benchmark/clip_benchmark/model_collection.py code served (permissive licence) · get_code("e02503f545c31203") |
| load_japanese_clip | Not yet run | eify/clip_benchmark/clip_benchmark/models/japanese_clip.py code served (permissive licence) · get_code("f5190e9b44c5f641") |
| path_to_bytes | Not yet run | eify/clip_benchmark/clip_benchmark/webdataset_builder.py code served (permissive licence) · get_code("eb9c4da61c3f9683") |
| value_from_first_key_found | Not yet run | eify/clip_benchmark/clip_benchmark/datasets/builder.py code served (permissive licence) · get_code("9e8b17a3977b594e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of $1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived from the LAION COCO dataset. We trained multiple models using image and text encoders of various sizes and kept different parts of the model frozen during the training. We thoroughly analyzed the trained models using existing evaluation datasets and newly created XTD200 and Flickr30k-200 datasets. We show that NLLB-CLIP is comparable in quality to state-of-the-art models and significantly outperforms them on low-resource languages.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2309.01859")
get_code_for_paper("2309.01859")
have("2309.01859")
Connect an agent — have() is free.