Comments (3)
Hi Prateek,
Thanks for your interest in our work and your great questions!
-
I did not evaluate the standard few-shot and zero-shot setting for the base ViT model, since they are not directly related to continual learning. However, one can treat one of the baselines -- GDumb -- as a few-shot learning method. To my understanding, GDumb trains on the buffered data only, which is the subsampled full dataset.
-
I believe I conducted such experiments, but not showed it in the L2P paper. However, I have to say task-specific prompts are not directly applicable to class-incremental learning, since you have no idea how to choose task-specific prompts at inference when the task ID is unknown. If I remember correctly, task-specific prompt did a bit worse than L2P on CIFAR100, but is comparable or better than L2P on 5-datasets. Intuitively, task-specific prompt does not have the ability to share knowledge between tasks, so that might be the reason. Nevertheless, feel free to add your experiments if you are interested and correct me if I am wrong.
Best,
Zifeng
from l2p.
The reason why I asked for zero/few shot number is that I suspect that the model might perform well even when we prepend some random vectors or slightly trained vectors along with the input image because the ViT model is pre-trained on ImageNet21k and CIFAR100 is very similar to it but easier. If the model has good zero/few-shot performance then it invalidates some of the claims made in the paper regarding continual learning and preventing forgetting.
Furthermore, if the performance is not better than task specific prompts then the claim regarding sharing knowledge might not be well supported as well. This comparison is completely skipped in the paper which I guess if the most important method to compare with.
Thanks,
Prateek
from l2p.
DualPrompt validates that share prefixtuning is better in paper 5.4?
from l2p.
Related Issues (20)
- Using different ViT and ResNet based models in L2P HOT 1
- RESOURCE_EXHAUSTED: Out of memory while trying to allocate # bytes.
- Bug in classifier?
- Reproduce issue
- Evaluation metrics on CORe50 HOT 1
- Loss become NaN. Results mismatch between different convolution algorithms. HOT 1
- Questions about the reproducibility of the code and the results of the paper HOT 9
- about providing the class orders. HOT 1
- Confusion about the ImageNet-R dataset HOT 2
- Inference HOT 9
- Question regarding the average and last accuracy. HOT 1
- Question regarding on FT-seq-Frozen
- Questions about the pre-trained ViT HOT 1
- reproducing 5-datasets with dualprompt
- Questions about domain-incremental setting, positional embedding and location of prompt HOT 3
- question on the G(eneral)-Prompt learning HOT 1
- DualPrompt: The Results without Prompts HOT 1
- Regarding transferring previous learned prompt params to the new prompt HOT 1
- Question about the t-SNE visualization of prompts (Figure 4)
- Transfer prompt parameter during training process. 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 l2p.