H11-M14_CODE.zip
From the dataset abstract
Method 為了使細胞實例分割模型具有持續性學習的能力，本方法以兩階段的實例分割模型為框架,加入輸出層級以及特徵層級的知識蒸餾以解決持續性學習裡的災難性遺忘問題,並且以偽標籤方法來解決來解決背景偏移問題，使得模型可以持續學習新資料以及新類別。 Usage 能用於持續性學習之細胞分割模型 Release Note v1.0.0, 2023/07/11...
Source: H11-M14_持續性學習之影像分割模型
Additional Information
| Field | Value |
|---|---|
| Data last updated | October 10, 2023 |
| Metadata last updated | July 11, 2023 |
| Created | July 11, 2023 |
| Format | application/zip |
| License | Other (Non-Commercial) |
| created | over 2 years ago |
| format | ZIP |
| id | 7be3744c-dfea-42f4-9309-558c2a809cd4 |
| last modified | over 2 years ago |
| md5 | bd47f41d79cf229605909f344c7b65cf |
| mimetype | application/zip |
| on same domain | True |
| package id | 865cfd97-8498-449f-9780-4d041629e4d9 |
| proxy url | https://scidm.nchc.org.tw/en/dataset/865cfd97-8498-449f-9780-4d041629e4d9/resource/7be3744c-dfea-42f4-9309-558c2a809cd4/nchcproxy/H11-M14_CODE.zip |
| revision id | 8a10a645-8416-4e24-965d-c8556c2592f7 |
| sha256 | 08bdd373df2123945c7fa3b50d7b1ce4520fb8c1c02a99be1a02c697214b7911 |
| size | 117.4 MiB |
| state | active |
| url type | upload |
推薦資料集：