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
0 votes
0 answers
6 views

How to train DINO on images with varying length (excluding padding options)?

I would like to train DINO (Emerging Properties in Self-Supervised Vision Transformers) on spectrograms of different size (specifically: different number of time bins and same number of frequency bins)...
user avatar
  • 1
0 votes
1 answer
54 views

1D Sequence Classification with self-supervised learning

I am working on a multi-class classification task on long one-dimensional sequences. The sequence length may vary in the range $[512, 30720]$, and there is one feature associated each time-step in the ...
user avatar
  • 101
0 votes
0 answers
23 views

Why does the feature space of an autoencoder typically contain more info than a teacher-student model?

This is a question our Prof gave us as exam preparation, but I don't know why the Autoencoder should contain more info than the Teacher Student model. Teacher Student Models are a class of models in ...
user avatar
  • 348
0 votes
2 answers
78 views

How do multimodal models establish connections between different modes?

I am specifically interested in data2vec, Meta's new model that can convert image, text, and sound data into a unified neural network representation. To my understanding, they did this through self-...
user avatar
1 vote
1 answer
72 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 ...
user avatar
0 votes
0 answers
15 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 ...
user avatar
  • 101
1 vote
0 answers
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 ...
user avatar
  • 11
0 votes
0 answers
18 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) ...
user avatar
0 votes
0 answers
24 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 ...
user avatar
2 votes
2 answers
148 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 ...
user avatar
2 votes
0 answers
73 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-...
user avatar
  • 121
2 votes
1 answer
71 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 ...
user avatar
2 votes
1 answer
82 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 ...
user avatar
  • 1,211
2 votes
1 answer
178 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 ...
user avatar
3 votes
1 answer
1k 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, ...
user avatar
1 vote
1 answer
61 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?
user avatar
1 vote
1 answer
263 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 ...
user avatar
  • 143
3 votes
1 answer
216 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-...
user avatar
  • 143
5 votes
2 answers
725 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 ...
user avatar
11 votes
3 answers
9k 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?
user avatar
  • 261
85 votes
3 answers
77k views

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?
user avatar
  • 33.8k
0 votes
1 answer
1k 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 ...
user avatar
13 votes
2 answers
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 ($...
user avatar
  • 946