Comments (7)
Hi, some researchers in semi-supervised segmentation area may like to use CE loss for CityScapes (as you mentioned). However, OHEM is a common setting in sueprvised training setting on CityScapes. Since it brings no computational cost/parameters during inference, why do we deliberately use a lower baseline (e.g. with CE loss)?
I also want to clarify two points:
- When compared with SOTA on Cityscapes, we use OHEM loss (on labeled set) for all the methods so the comparison is fair (their supervised baseline is exactly the same one).
- If the baseline for semi-supervised learning is very low, the gain may be large and seems that the semi-supervised method have a very large impact on the performance. However, it that true? I think, we study semi-supervised learning in order to use unlabeled data to improve the performance of the model, not to see large gains on a low baseline.
from torchsemiseg.
Hi, for supervised training, we use OHEM loss on CityScapes and CE loss on VOC dataset, which is a common setting in Semantic Segmentation. We haven't tried CE loss on CityScapes for supervised training.
For CPS loss, we use CE loss for both the two datasets.
from torchsemiseg.
In my opinion, for semi-supervised training, all methods use CE loss for both the two datasets. The baseline of Deeplab v3+ with ResNet-101 on 1/8 cityscapes setting is 72-73 in your paper. However, in A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation, the result is only 68.9.
from torchsemiseg.
I think if the supervised baseline is not trained well enough, then we cannot tell where the gain brought by semi-supervised learning actually comes from.
from torchsemiseg.
Yeah, I agree with you that studying semi-supervised learning on a higher baseline. I'm sorry for that I havn't noticed that you reproduce all the SOTA methods by yourself. Maybe you can point it on the benchmark, https://paperswithcode.com/task/semi-supervised-semantic-segmentation. Or other people may be confused by the big margin. That's only my own point and please forgive me if I bother you.
from torchsemiseg.
Hi, I know what you mean. However, the benchmark website you provide is just a reference. The comparisons in it are not fair at all, for example, they didn’t even use the same data partition (i.e. the same 1/8 subset of PASCAL VOC).
from torchsemiseg.
Thanks for your kind and quick reply.
from torchsemiseg.
Related Issues (20)
- questions about the results HOT 4
- Question about training HOT 2
- About the batchsize with CutMIx on CItyscapes HOT 1
- code running error HOT 1
- docker error HOT 1
- cutmix question HOT 1
- Labeled and Unlabeled dataloaders HOT 1
- pretrained parameter HOT 1
- CPS loss
- Pseudo labeling question HOT 2
- training with one GPU HOT 4
- About the explaination of Single-network pseudo supervision
- a question about CPC you mentioned in your paper HOT 2
- File-related questions.
- About the cps_weight with different labeled_ratio HOT 1
- Questions related to Cut-Mix. HOT 1
- Questions about CPS loss. HOT 2
- Image present in both labeled and unlabeled splits HOT 2
- Memory and Inf time (fps) for CPS HOT 2
- Question about the batchnorm while trainning HOT 1
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 torchsemiseg.