[ICML2025] Official Implementation of CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
active 2025-05-02 → 2026-06-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 398 days from 2025-05-02 to 2026-06-03. Pushes: 65 total, peak 12 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 20 total, peak 4 in a day. Comments: 51 total, peak 6 in a day. Stars: 53 total, peak 7 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| ZHE-SAPI | 76 | 47 | 0 | 27 |
| pluto-8 | 4 | 0 | 0 | 4 |
| Yager-42 | 4 | 0 | 0 | 2 |
| Lhy-opt | 4 | 0 | 0 | 3 |
| mcmingchang | 4 | 0 | 0 | 2 |
| dongguazi | 2 | 0 | 0 | 1 |
| PonyPinkPie | 2 | 0 | 0 | 1 |
| sjnkup | 1 | 0 | 0 | 0 |
| Amina-Mokhtar | 1 | 0 | 0 | 1 |
| IceIce1ce | 1 | 0 | 0 | 0 |
| A-Cycle-M | 1 | 0 | 0 | 0 |
| Mengwei-Sun | 1 | 0 | 0 | 1 |
| NielsRogge | 1 | 0 | 0 | 0 |
| Rudder573 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#18ZHE-SAPI2026-02-03 19:18如何应用到CNN模型下的检测？
- Issue#23Rudder5732026-02-03 18:17Different metrics but got exactly the same visulization results
- Issue comment#22ZHE-SAPI2025-12-08 03:29算法实现细节及合理性问题
- Issue comment#22ZHE-SAPI2025-12-08 03:23算法实现细节及合理性问题
- Issue comment#22ZHE-SAPI2025-12-08 02:53算法实现细节及合理性问题
- Issue#21A-Cycle-M2025-11-17 14:27Where can I find the weights for DiscriminativeSubNetwork_3d_att_dino_channel line 883 from CostFilter-AD/Costfilter_Glad/Costfilter_Glad_Mvtecad /main_multi_glad_dino_gauss_3d_qianghua.py
- Issue comment#20ZHE-SAPI2025-11-13 09:36Missing epoch_23_hvq_my_mvtecad.pth for Costfilter_HVQ_mvtec
- Issue comment#20Amina-Mokhtar2025-11-13 09:33Missing epoch_23_hvq_my_mvtecad.pth for Costfilter_HVQ_mvtec
- Issue comment#20ZHE-SAPI2025-11-13 09:26Missing epoch_23_hvq_my_mvtecad.pth for Costfilter_HVQ_mvtec
- Issue comment#16ZHE-SAPI2025-11-13 09:21如何获得costfilter_dinomaly_mvtec_uni_my_train_test.py中过的权重model_10000.pth
- Issue comment#16dongguazi2025-11-03 08:30如何获得costfilter_dinomaly_mvtec_uni_my_train_test.py中过的权重model_10000.pth
- Issue comment#19Mengwei-Sun2025-10-19 02:06关于权重加载问题
- Issue comment#18ZHE-SAPI2025-10-17 13:33如何应用到CNN模型下的检测？
- Issue comment#17Yager-422025-09-28 00:14指标疑问
- Issue#17Yager-422025-09-28 00:14指标疑问
- Issue comment#17ZHE-SAPI2025-09-27 23:53指标疑问
- Issue#17ZHE-SAPI2025-09-27 23:51指标疑问
- Issue comment#17ZHE-SAPI2025-09-27 23:51指标疑问
- Issue comment#17Yager-422025-09-25 02:46指标疑问
- Issue#17Yager-422025-09-23 02:55指标疑问
- Issue comment#16ZHE-SAPI2025-09-18 09:22如何获得costfilter_dinomaly_mvtec_uni_my_train_test.py中过的权重model_10000.pth
- Issue#16dongguazi2025-09-15 03:00如何获得costfilter_dinomaly_mvtec_uni_my_train_test.py中过的权重model_10000.pth
- Issue comment#15mcmingchang2025-09-10 03:36我基于Costfilter_Dinomaly添加了dinov3的base版本
- Issue comment#11pluto-82025-09-04 02:08model
- Issue comment#15ZHE-SAPI2025-09-03 17:12我基于Costfilter_Dinomaly添加了dinov3的base版本
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 53 stars here means stars gained during the window, not the repo's star count.