Questions tagged [self-supervised-learning]

For questions related to self-supervised learning (SSL), which typically refers to techniques that automatically generate the supervisory learning signal. SSL can be used for representation learning, so it can be useful for transfer learning too. Some people consider SSL a sub-field of unsupervised learning given that many (if not all) SSL techniques do not require a human to manually annotate the inputs.

Filter by
Sorted by
Tagged with
1
vote
0answers
13 views

Perform clustering on high dimensional data

Recently I trained a BYOL model on a set of images to learn an embedding space where similar vectors are close by. The performance was fantastic when I performed approximate K-nearest neighbours ...
0
votes
0answers
13 views

Self-Supervised learning model that labels the similar/not similar output?

I want to first reference the following SimCLR framework illustration to explain better what I'm asking. Lets say that after I found out of the image is not similar to the cat, can I actually predict ...
1
vote
0answers
19 views

How do the scale of an embedding affects a downstream task?

I am currently training a neural network in a self-supervised fashion, using Contrastive Loss and I want to use that network then to fine-tune it in a classification task with a small fraction of the ...
0
votes
0answers
14 views

Do Self Organizing Maps (SOMs) require as much data as a typical neural network?

The question is in the title. I'm looking at clustering sequences and have created a short-list of approaches: Clustering on Edit Distance: Needleman-Wunsch: Similarity measure (used in ESAC) ...
0
votes
0answers
19 views

What is the motivation for using a memory bank in contrastive learning?

... and not specifically the memory bank (see section "3 Learning with A Memory Bank" in the link), but any other alternative method that solves the same problem. My point is that I'm not ...
0
votes
0answers
27 views

What is the purpose of key - query matching in Momentum Contrastive Learning?

I am trying to understand the intuition behind the MoCo paper. How does the algorithm know if the key and query are crops from the same image?
2
votes
2answers
113 views

Is it realistic to train a transformer-based model (e.g. GPT) in a self-supervised way directly on the Mel spectrogram?

In music information retrieval, one usually converts an audio signal into some kind "sequence of frequency-vectors", such as STFT or Mel-spectrogram. I'm wondering if it is a good idea to ...
2
votes
0answers
55 views

Does Yann LeCun consider k-means self-supervised learning?

I was discussing the topic of self-supervised learning with a colleague. After a while we realized we were using different definitions. That's never helpful. Both of us were introduced to self-...
2
votes
1answer
65 views

What are some most promising ways to approximate common sense and background knowledge?

I learned from this blog post Self-Supervised Learning: The Dark Matter of Intelligence that We believe that self-supervised learning (SSL) is one of the most promising ways to build such background ...
0
votes
0answers
19 views

Why does self-supervised representation learning (such as SimpleSiam) use a ResNet encoder that is trained in a supervised fashion?

Can anybody explain to me why does self-supervised representation learning on images using Siamese neural networks (such as SimpleSiam (https://arxiv.org/abs/2011.10566), SimCLR, Boyl) use a ResNet ...
2
votes
1answer
63 views

Is it possible to use self-supervised learning on different images for the pretext and downstream tasks?

I have just come across the idea of self-supervised learning. It seems that it is possible to get higher accuracies on downstream tasks when the network is trained on pretext tasks. Suppose that I ...
2
votes
1answer
138 views

Is it possible to pre-train a CNN in a self-supervised way so that it can later be used to solve an instance segmentation task?

I would like to use self-supervised learning (SSL) to learn features from images (the dataset consists of similar images with small differences), then use the resulting trained model to bootstrap an ...
3
votes
1answer
824 views

How to generate labels for self-supervised training?

I've been reading a lot lately about self-supervised learning and I didn't understand very well how to generate the desired label for a given image. Let's say that I have an image classification task, ...
1
vote
1answer
59 views

Is there a way to get landmark features automatically learned by a neural network?

Is there a way to get landmark features automatically learned by a neural network without having to manually pre-label them in the images that are being fed into the network?
1
vote
1answer
175 views

What is the difference between distant supervision and self-supervision?

Weak supervision is supervised learning, with uncertainty in the labeling, e.g. due to automatic labeling or because non-experts labelled the data [1]. Distant supervision [2, 3] is a type of weak ...
3
votes
1answer
187 views

Does self-supervised learning require auxiliary tasks?

Self-supervised learning algorithms provide labels automatically. But, it is not clear what else is required for an algorithm to fall under the category "self-supervised": Some say, self-...
5
votes
2answers
634 views

How to understand the concept of self-supervised learning in AI?

I am new to self-supervised learning and it all seems a little magical at the moment. The only way I can get an intuitive understanding is to assume that, for real-world problems, features are still ...
11
votes
3answers
8k views

What is the relation between semi-supervised and self-supervised visual representation learning?

What's the differences between semi-supervised learning and self-supervised visual representation learning, and how they are connected?
80
votes
3answers
72k views

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?
0
votes
1answer
951 views

What is the purpose of the GAN?

The Generative Adversarial Network (GAN) is composed of a generator $G$ and a discriminator $D$. How do these two components interact? What is the intuition behind the GAN, its purpose, and how it is ...
13
votes
2answers
2k views

How are generative adversarial networks trained?

I am reading about generative adversarial networks (GANs) and I have some doubts regarding it. So far, I understand that in a GAN there are two different types of neural networks: one is generative ($...