Comments (3)
Hi, thanks for noticing it and raising the question.
Generally speaking, the annotations of labeled images in Table.1 and Table.2 are of different qualities.
Specifically, the Pascal VOC 2012 training set originally contains 1,464 high-quality annotations. Later it is augmented by extra 9,118 lower-quality annotations from the SBD dataset to form 10,582 image-masks pairs.
The labeled images in Table.1 are randomly selected from the augmented training set with 10,582 imaages in total, while the labeled images in Table.2 are selected from the high-quality original training set with 1,464 images in total. Please refer to the first sentence of the table caption for difference. By the way, the unlabeled images are both the remaining images in the augmented training set.
The settings of Table.1 follow the mainstream practice in recent works like Context-aware Consistency , while Table.2 follows the state-of-the-art method PseudoSeg.
from st-plusplus.
That's clarify a lot.
Thanks very much!
from st-plusplus.
The experiments in Table 1 were performed on which division of Pascal VOC?
from st-plusplus.
Related Issues (20)
- pseudo- labels生成之后,更新labelled data的问题 HOT 2
- Why "Re-initialize S" in Algorithm2? HOT 2
- 作者你好,我想问一下unlable.txt的文件怎么来的。unlable的标签不应该是没有的吗? HOT 4
- Experiments Question HOT 1
- 有关于灰度图像 HOT 1
- torch.version? HOT 1
- Using the best model to do pseudo labeling HOT 2
- 最终的IOU HOT 3
- How to deal with the descending in retraining with all data in mode of ST++? HOT 4
- 监督训练过程 HOT 3
- 训练过程中的报错 HOT 1
- 数据集的文件放置 HOT 2
- @yyamx 你好,你使用的是Pasca VOC数据集吗?
- 测试验证集
- RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM HOT 2
- 关于 checkpoints 程式码和论文的叙述,似乎不同
- How to test our own custom data set? HOT 3
- 测试集评估代码 HOT 4
- 预训练模型选择
- mode test
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from st-plusplus.