Feng Zhu, Rui Zhao, Lei Bai, Wanli Ouyang, Yizhou Wang, Fengwei Yu, Meilin Chen, Donglian Qi, Shixiang Tang, Yuanzheng Ci
We lifted 13 functions out of this paper's own repositories and ran 8 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 |
|---|---|---|
| OpenGVLab/UniHCP | canonical | 8 of 13 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | OpenGVLab/UniHCP/core/utils.py code served (permissive licence) · get_code("78d1f9f766be74b7") |
| accuracy_multi | Ran | OpenGVLab/UniHCP/core/utils.py code served (permissive licence) · get_code("8a63c5da44344ba6") |
| flat | Ran | OpenGVLab/UniHCP/core/config.py code served (permissive licence) · get_code("4570d6d70bccdfb6") |
| init | Ran | OpenGVLab/UniHCP/core/fp16/amp.py code served (permissive licence) · get_code("eb8a2600afc1de95") |
| param_group_fc | Ran | OpenGVLab/UniHCP/core/make_param_group.py code served (permissive licence) · get_code("70165e0988ce9571") |
| param_group_multitask | Ran | OpenGVLab/UniHCP/core/make_param_group.py code served (permissive licence) · get_code("e4a7663d686ce91a") |
| param_group_no_wd | Ran | OpenGVLab/UniHCP/core/make_param_group.py code served (permissive licence) · get_code("0540cf098dbc3d42") |
| retry_if_cuda_oom | Ran | OpenGVLab/UniHCP/core/memory.py code served (permissive licence) · get_code("ff1253be17efe1ae") |
| dist_init | Not yet run | OpenGVLab/UniHCP/core/distributed_utils.py code served (permissive licence) · get_code("82c208a1743fdfc6") |
| float_function | Not yet run | OpenGVLab/UniHCP/core/fp16/amp.py code served (permissive licence) · get_code("f27c7ab614e20039") |
| half_function | Not yet run | OpenGVLab/UniHCP/core/fp16/amp.py code served (permissive licence) · get_code("6b4eee4b4bb1f238") |
| simple_group_split | Not yet run | OpenGVLab/UniHCP/core/distributed_utils.py code served (permissive licence) · get_code("b1471eccec180d87") |
| specific_group_split | Not yet run | OpenGVLab/UniHCP/core/distributed_utils.py code served (permissive licence) · get_code("4e36f197c125d4d3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Human-centric perceptions (e.g., pose estimation, human parsing, pedestrian detection, person re-identification, etc.) play a key role in industrial applications of visual models. While specific human-centric tasks have their own relevant semantic aspect to focus on, they also share the same underlying semantic structure of the human body. However, few works have attempted to exploit such homogeneity and design a general-propose model for human-centric tasks. In this work, we revisit a broad range of human-centric tasks and unify them in a minimalist manner. We propose UniHCP, a Unified Model for Human-Centric Perceptions, which unifies a wide range of human-centric tasks in a simplified end-to-end manner with the plain vision transformer architecture. With large-scale joint training on 33 humancentric datasets, UniHCP can outperform strong baselines on several in-domain and downstream tasks by direct evaluation. When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e.g., 69.8 mIoU on CIHP for human parsing, 86.18 mA on PA-100K for attribute prediction, 90.3 mAP on Market1501 for ReID, and 85.8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task. The code and pretrained model are available at https://github.com/OpenGVLab/UniHCP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.02936")
get_code_for_paper("2303.02936")
have("2303.02936")
Connect an agent — have() is free.