[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation
active 2023-08-24 → 2025-11-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 803 days from 2023-08-24 to 2025-11-03. Pushes: 1 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 5 total, peak 1 in a day. Comments: 6 total, peak 1 in a day. Stars: 115 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Pull request#132ikanamazu2025-02-14 16:30
- Issue#131KKWY09092024-12-30 06:59Preservation of model weights
- Issue#130KKWY09092024-12-24 13:08Failed to use random crop
- Issue comment#129akang-ai2024-12-04 08:42代码请求
- Issue comment#129akang-ai2024-11-24 03:16代码请求
- Issue#128Run-192024-10-10 08:36Could you tell me where can I find the code for multiplying the DICE loss with the classification score that you mentioned in your paper?
- Issue comment#127LL-LIN2024-05-11 07:24自定义数据集上训练的详细教程
- Issue comment#121FrankFeng-232024-01-27 06:17Is lightweight backbone like mobilenet available in the future?
- Issue comment#100nai-kon2024-01-23 00:23Bug of `demo.py`
- Issue#127wjpstudy2023-12-12 09:57自定义数据集上训练的详细教程
- Issue#126Zhounjau2023-12-06 08:54loss_mask:nan
- Issue comment#124lsm1402023-08-24 08:12training details
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 115 stars here means stars gained during the window, not the repo's star count.