For questions related to zero-shot learning, where training and test classes are disjoint. This problem can be tackled by solving related sub-problems, e.g. learning intermediate attribute classifiers.
Questions tagged [zero-shot-learning]
7 questions
4
votes
1 answer
What is the difference between fine tuning and variants of few shot learning?
I am trying to understand the concept of fine-tuning and few-shot learning.
I understand the need for fine-tuning. It is essentially tuning a pre-trained model to a specific downstream task.
However, recently I have seen a plethora of blog posts…
Exploring
- 223
- 6
- 16
1
vote
0 answers
What is the difference between prompt tuning and prefix tuning?
I read prompt tuning and prefix tuning are two effective mechanisms to leverage frozen language models to perform downstream tasks. What is the difference between the two and how they work really?
Prompt Tuning:…
Exploring
- 223
- 6
- 16
1
vote
1 answer
Using a pre-trained model to generate labels to data to then train a model on
I'm trying to set up a pipeline for my ML models to automatically re-train themselves whenever concept drift occurs to recalibrate to the new output distributions. However, I can't get ground-truth from my data without manual labeling, and I want an…
Sanger Steel
- 11
- 1
1
vote
0 answers
What is meant by "Zero-Shot Visual Recognition"?
Many recent research papers contain the phrase "Zero-Shot Visual Recognition".
What exactly is meant by zero-shot visual recognition? Does the task need only images or also the other data like text?
hanugm
- 3,571
- 3
- 18
- 50
0
votes
0 answers
Train/Validation/Test split in Zero-Shot learning?
Is it recommended to do test/validation epochs in zero shot learning tasks? how can one split the unseen and seen classes in that case?
Can the validation set be a mixture of the two, under the assumption that we do not update the weights in…
Idan Tank
- 3
- 1
0
votes
2 answers
classification of unseen classes of image in open set classification
I have a scanned image, and they need to be classified in one of the pre-defined image classes, so that it can be sorted. However, the problem is the open nature of the classes. At testing time, new classes of scanned images can be added and the…
Rambo_john
- 26
- 6
0
votes
1 answer
Zero shot learning available labels in testing set
As we all know, zero shot learning involves a model predicting classes that it has not seen. But we are given all the attributes each class might have.
Is it fair to assume that we are "aware" of all the class labels a dataset might have ?…
