Jian Wang, Jingdong Wang, Xinyu Zhang, Zhiyin Shao, Changxing Ding
We lifted 8 functions out of this paper's own repositories and ran 4 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 |
|---|---|---|
| zhiyinshao-h/unipt | canonical | 4 of 7 |
| ZhiyinShao-H/UniPT | — | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| basic_clean | Ran | zhiyinshao-h/unipt/clip/simple_tokenizer.py code served (permissive licence) · get_code("98f385d847636a3e") |
| get_pairs | Ran | zhiyinshao-h/unipt/clip/simple_tokenizer.py code served (permissive licence) · get_code("d919ae32e5e4e616") |
| resize_pos_embed | Ran | zhiyinshao-h/unipt/clip/model.py code served (permissive licence) · get_code("0570970b85b8d376") |
| whitespace_clean | Ran | zhiyinshao-h/unipt/clip/simple_tokenizer.py code served (permissive licence) · get_code("9542161e9640b858") |
| ViLTransformerSS | Not yet run | ZhiyinShao-H/UniPT/vilt/modules/vilt_module.py code served (permissive licence) · get_code("e7b6b004d47cf257") |
| build_model | Not yet run | zhiyinshao-h/unipt/clip/model.py code served (permissive licence) · get_code("2acf7b3d245de310") |
| get_pretrained_tokenizer | Not yet run | zhiyinshao-h/unipt/vilt/datamodules/datamodule_base.py code served (permissive licence) · get_code("6cc26ba2dedcb73e") |
| load | Not yet run | zhiyinshao-h/unipt/clip/clip.py code served (permissive licence) · get_code("db64af1ba3479e8d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The pre-training task is indispensable for the text-toimage person re-identification (T2I-ReID) task. However, there are two underlying inconsistencies between these two tasks that may impact the performance: i) Data inconsistency. A large domain gap exists between the generic images/texts used in public pre-trained models and the specific person data in the T2I-ReID task. This gap is especially severe for texts, as general textual data are usually unable to describe specific people in fine-grained detail. ii) Training inconsistency. The processes of pre-training of images and texts are independent, despite cross-modality learning being critical to T2I-ReID. To address the above issues, we present a new unified pre-training pipeline (UniPT) designed specifically for the T2I-ReID task. We first build a large-scale text-labeled person dataset "LUPerson-T", in which pseudo-textual descriptions of images are automatically generated by the CLIP paradigm using a divideconquer-combine strategy. Benefiting from this dataset, we then utilize a simple vision-and-language pre-training framework to explicitly align the feature space of the image and text modalities during pre-training. In this way, the pre-training task and the T2I-ReID task are made consistent with each other on both data and training levels. Without the need for any bells and whistles, our UniPT achieves competitive Rank-1 accuracy of, i.e., 68.50%, 60.09%, and 51.85% on CUHK-PEDES, ICFG-PEDES and RSTPReid, respectively. Both the LUPerson-T dataset and code are available at https://github.com/ZhiyinShao-H/UniPT.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2309.01420")
get_code_for_paper("2309.01420")
have("2309.01420")
Connect an agent — have() is free.