Comments (20)
By the way, there is a typo in your table, the supervision for works including yours should be I (Image) not S (Saliency) I think
from clims.
There are a lot of things to prepare recently and I hope to release the code in the coming months.
from clims.
By the way, there is a typo in your table, the supervision for works including yours should be I (Image) not S (Saliency) I think
Table 2?
from clims.
By the way, there is a typo in your table, the supervision for works including yours should be I (Image) not S (Saliency) I think
Table 2?
yes
from clims.
I'm trying to reproduce your result, but the training loss doesn't decrease at all...
In the Sec 3.3, you said the loss is log(s), in which s is a cosine similarity, so
from clims.
When I trying to reproduce, I use logit_scale to scale cosine similarity to logits \in [-100/7, 100/7] and then use logsigmoid to compute the loss, I wonder whether I use the correct format.
from clims.
When I trying to reproduce, I use logit_scale to scale cosine similarity to logits \in [-100/7, 100/7] and then use logsigmoid to compute the loss, I wonder whether I use the correct format.
I just use the cosine similarity between two vectors, norm(v1) * norm(v2).T
from clims.
When I trying to reproduce, I use logit_scale to scale cosine similarity to logits \in [-100/7, 100/7] and then use logsigmoid to compute the loss, I wonder whether I use the correct format.
In my experiments, the loss slightly decreased but the activation map gradually approached the target category.
from clims.
When I trying to reproduce, I use logit_scale to scale cosine similarity to logits \in [-100/7, 100/7] and then use logsigmoid to compute the loss, I wonder whether I use the correct format.
I just use the cosine similarity between two vectors, norm(v1) * norm(v2).T
but how to compute log on the cosine similarity less than 0
from clims.
clamp (0, 1)
from clims.
clamp (0, 1)
ok, I'll try that formation, thanks for your reply
from clims.
I hope to release the code in the coming months :-)
from clims.
I hope to release the code in the coming months :-)
Great!, by the way, could you please provide the pre-defined cbs set
from clims.
{'boat': ['a photo of river', 'a photo of water', 'a photo of lake', 'a photo of sea', 'a photo of building'],
'train': ['a photo of railroad', 'a photo of railway', 'a photo of branches', 'a photo of tree'], You can try this one.
from clims.
{'boat': ['a photo of river', 'a photo of water', 'a photo of lake', 'a photo of sea', 'a photo of building'], 'train': ['a photo of railroad', 'a photo of railway', 'a photo of branches', 'a photo of tree'], You can try this one.
Nice
from clims.
@Sierkinhane Sry to bother you again, could you please provide the finetuned CLIP model, I've finetuned the CLIP model using RN50 as backbone and got ~96% accuracy on VOC12 train_aug, but still failed to train CLIMS even only using loss_otm, the miou of CAMs on train set is only 19%
from clims.
I've found the code to finetune CLIP (openai/CLIP#83), I'll try it
from clims.
But I wonder whether I use F.multilabel_soft_margin_loss and treat finetuning CLIP as a multi-label classification task is correct
from clims.
Details were provided in email. : )
from clims.
@liberty-hit hello, the source code is released now.
from clims.
Related Issues (20)
- Training time HOT 2
- About The quality of initial CAMs HOT 5
- The difference between previous version with new version. HOT 3
- about deeplab setting HOT 2
- When will the code of COCO be released? HOT 25
- 请问如何Finetune CLIP模型? HOT 1
- Ran out of input HOT 1
- 是否可提供训练好的权重档作复现? HOT 1
- Error on load_img_name_list function HOT 5
- Undefined Function get_dataset HOT 15
- How to obtain pre-trained baseline CAM HOT 14
- Need Coco baseline scores HOT 3
- Please check the Pascal VOC train_aug. HOT 2
- 读取数据集出现错误 HOT 2
- Creation of sem-seg HOT 2
- Problem Solve
- How to extract background image features HOT 4
- How to train DeepLabV1-R38 ? HOT 1
- irnet on coco HOT 6
- test time HOT 2
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 clims.