Questions tagged [transfer-learning]

A setting in machine learning when a model trained in one context/domain should then be applied to a different (but related) context/domain.

Filter by
Sorted by
Tagged with
0
votes
0answers
8 views

Transfer learning and forecasting: Are there methods to transfer learning of regressor impact on time series?

We have 3 time series namely sales time series A, time series B and sales time series C. I want to forecast A and C. B is an available regressor to A. Let's say we know that B has a negative impact ...
0
votes
0answers
21 views

Keras model with Google BERT -> very low accuracy [duplicate]

I'm attempting to fine-tune Google BERT to be able to classify some text to a single integer label (multiclass classification). I have the model up and running, however the predicted labels are all ...
1
vote
0answers
14 views

Multiple-domain adaptation vs multi-task learning

I am confused with the definitions of domain adaptation and multi-task learning. I have K datasets, each with the same feature and label space and thus the same learning problem, but with different ...
0
votes
1answer
13 views

Slower training after transfer learning

Before I used a model to categorize cars, bikes and bicycles that looked like this: ...
0
votes
1answer
22 views

Can a pretrained Deep learning model of objects (chair, table) be used to do transfer learning and classify telecom equipment?

I want to classify telecom devices: switches, routers, etc. I know that there are pre-trained model available online: https://github.com/tensorflow/models Will it be possible to use transfer ...
0
votes
0answers
19 views

Transfer learning: Which layers should be fine-tuned in encdoer decoder model?

I've a pretrained model having encoder-decoder architecture, which was trained on a dataset A by using Imagenet pretrained ...
3
votes
2answers
1k views

What's the intitution behind contrastive learning or approach?

Maybe a noobs query, but recently I have seen a surge of papers w.r.t contrastive learning (a subset of semi-supervised learning). Two recent papers which I read, which detailed this approach are: ...
0
votes
0answers
11 views

Domain Adaptation - Cross Domain Model better than Within Domain Model

I have three domains, A, B, and C. For these domains I use cross validation to train both within and cross-domain models. The results look something like this: Source A and Target A: Kappa = .25 ...
0
votes
0answers
12 views

Looking for transfer learning references

I am looking for transfer learning papers where the training was done on a small number of classes and the transfer model predict a largest number of classes.
0
votes
0answers
34 views

Differences between Transfer Learning and Meta Learning

What are the differences between meta learning and transfer learning? I have read 2 articles on Quora and TowardDataScience. ...
0
votes
1answer
33 views

The negative transfer problem in machine learning?

I can find the definition of negative transfer on Wikipedia: In behavioral psychology, negative transfer is the interference of the previous knowledge with new learning, where one set of events ...
0
votes
1answer
50 views

Is autoencoder for anomaly detection a transfer learning?

I am doing a binary classification with unsupervised learning. I learn an autoencoder on samples from class0 and then predict samples from both class0 and class1. Then I classify sample according to ...
0
votes
0answers
31 views

Add new words into the vocabulary in transfer learning?

I learned that if we fine-tune a task based on a pre-trained model and the vocab of the new task is relatively small compared to the original pre-trained model we usually fix the embedding layer. ...
1
vote
2answers
47 views

Why does a colormap such as viridis give better results for spectrogram-based audio classification over greyscale?

I have been trying audio classification on the UrbanSound8k dataset and MPSSC snore classification dataset. I am using the approach of transfer learning by extracting features from AlexNet and VGG19 ...
0
votes
1answer
47 views

What is the difference between transfer learning and reinforcement learning?

...Seems so similar to me... I am new in advanced ML techniques, please give me some example.
0
votes
0answers
11 views

How to apply transfer learning using a survival model?

I have a parametric survival model assuming a certain distribution pattern for dataset A. I now wish to use the same model for dataset B. What criteria is needed to ensure that the model built on ...
0
votes
2answers
59 views

Directly using Inaccurate Labels vs. Transfer Learning

I have a two ML models model_a and model_b that optimize on an event, label_a. I have a small volume of labels for model_a and a large volume of labels for model_b. The features used in these models ...
1
vote
0answers
138 views

Transfer Learning for non-NN models

I have built an non-NN Ensemble Classifier for labeling the content of scanned invoices, for which I used a training set of template invoices. I would like to use that model to predict labels of ...
0
votes
1answer
23 views

Testing machine learning models using a different set of labels

I have a dataset with 119 features and 228 samples. I have trained my classifier using a particular set of labels (0 and 1). Now I want to test how the model is performing to external data. There is ...
1
vote
1answer
61 views

Object detection with just one image? [duplicate]

Deep neural networks require lots of examples to learn tasks like image classification, and object recognition. On the other hand, we humans can learn and identify object just by looking at it once. ...
0
votes
0answers
67 views

MSE loss going Infinite [duplicate]

I am using DeepLabv3+ model to perform regression and predict the value of one of the channels. Details of the model used OS = 8, Backbone = None, loss='mean_squared_error', optimizer = adam(0.001, ...
0
votes
0answers
41 views

how to choose a transfer learning approach for regression model

I am new to the concept of transfer learning and from what I have seen so far, there are many ways in which transfer learning can be applied. I have two datasets where the distribution of failures ...
2
votes
0answers
104 views

Why we need the Gram matrix in style transfer learning?

I read this paper by Gatys and cannot comprehend why the Gram matrix for the style feature maps is necessary? In the paper it reads that: On top of the CNN responses in each layer of the network ...
2
votes
1answer
41 views

Combining data with differing dependent variables

Suppose we have two feature matrices, $X_1$ and $X_2$, with response variables $Y_1$ and $Y_2.$ Where $X_1$ and $X_2$ have the same feature columns, but distinct observations. Furthermore, $Y_1$ and $...
0
votes
1answer
40 views

Understanding the process of transfer learning for NLP

Full Disclosure: I am a machine learning newbie. I have been learning about natural language processing for the past few weeks. To my understanding, the process of creating a supervised text model ...
0
votes
0answers
27 views

What type of Normalisation technique is best for image data before applying any CNN deep learning model on type of it? [duplicate]

How to decide upon the normalisation that need to be used for image classification or cv problems , Is there any standard on what to choose when in particularly with Image data ?
1
vote
0answers
15 views

Needing 4th dimension for shape [closed]

I was working on a transfer learning solution to categorize between diseases in the eye. I was using the Xception model built into Keras and it uses a data set that I was able to accumulate. However ...
1
vote
0answers
23 views

Supervised learning in non-stationary environments?

For real applications, concept drifts often exist, i.e., the relationship between the input and output changes overtime. I'm wondering what are the most common methods to enable neural networks to ...
0
votes
0answers
45 views

How to do transfer learning with limited data

This is my first question here, please be gentle with me. I'm working on point cloud classification problem. I'm building a NN to classify point cloud. I found a really nice architecture that I want ...
2
votes
1answer
31 views

Using a separate but related dataset for feature extraction (transfer learning)

I have two datasets of MRI images: a larger one of Altzheimer's paitents (AD), which is about 3 times the size of a smaller dataset of brain tumor paitents (BT). My aim is to make use of the AD data ...
2
votes
0answers
24 views

Transfer Learning in domains other than Image processing and NLP

Can Transfer Learning be applied in domains other than Image processing or NLP? I am trying to apply it on clickstream data (for propensity modeling). Any reference would be greatly appreciated.
1
vote
1answer
15 views

Same input size for Source and Target Model?

For the transfer learning do we need to have same input image size of target model as source model? for example my source model is trained on 100x100 input images and target model is low resolution ...
0
votes
1answer
410 views

Transfer learning for regression problems?

How does transfer learning work for regression tasks? Can someone point to an application where transfer learning has been successfully applied for regression tasks.
1
vote
0answers
20 views

What do I call the model that I have “transferred” from in transfer learning?

I am trying to document some machine learning artefacts, we have two models a and b. a and b are trained using the same data, they are trained with the same embedding and with the same algorithm and ...
5
votes
3answers
181 views

Extending a neural network to classify new objects

Suppose a model M classifies apples and oranges. Can M be extended to classify a third class of objects, e.g., pears, such that ...
3
votes
1answer
2k views

How to Fine Tune a pre-trained network

I'm looking into using Transfer Learning to take the ResNet50 model trained on ImageNet and fine tune it to my own dataset using Keras. However, I feel I have some misconception about what exactly ...
1
vote
0answers
401 views

compute the KL divergence between two datasets

I have two datasets $D1$ and $D2$ in two different feature spaces $\mathcal{X}_{1} \in \Re^{m}$ and $\mathcal{X}_{2} \in \Re^{n}$. Further assume that the datasets have different number of data points....
1
vote
0answers
75 views

Would training 1024x1024 images with pretrained resnet (224x224) be appropriate?

I want to use Resnet50 (or 101, or 152..) backbone for a segmentation task. My problem requires a lot of context, hence tiling the large image into 224x224 defeats the purpose. I was wondering if I ...
1
vote
0answers
121 views

Using PCA in domain adaptation

In literature, I see people using (Kernelized) Principle Component Analysis, not for feature extraction, but for domain adaptation. In other words, I have data from a source domain and I would like to ...
0
votes
1answer
97 views

What does a “similar” dataset mean in the context of fine tuning a CNN?

In https://arxiv.org/pdf/1809.09529.pdf it is said If the new dataset is similar to original dataset, we expect higher-level features in the CNN to be relevant to this dataset. Thus, it is ...
8
votes
1answer
2k views

How should I standardize input when fine-tuning a CNN?

I am working on a model for binary classification of skin samples from https://www.isic-archive.com as either benign or malignant. I want to use the VGG16 model pre-trained on ImageNet and fine-tune ...
0
votes
1answer
17 views

Should I be stepping down high a dimensional embedding when predicting low dimensional output

I'm using a ResNet-50 pretrained on ImageNet as a starting point for various image classifiers. Because the pretrained model has 1001 outputs, I have added a single dense layer with output size 500 ...
0
votes
1answer
182 views

using (deep) neural networks for a severely imbalanced image dataset when some classes have <10 images

Taking a long shot here. So I have a a small dataset of ~500 images with discrete labels from 1 to 9. My task is to detect the per-class and overall accuracy of this classification method using a (...
0
votes
1answer
445 views

Is Gradient Boosting Regression Tree able to learn linear models

Assume $Y$ is a linear function of a vector of variables $X$ (plus a noise term). The train data consists of ($X,Y$) such that $X \in [0,1]$. Assume one use gbdt to learn this linear model. And if ...
0
votes
0answers
27 views

FineTuned VGG16 achieving great results on epoch 1, is this normal?

I'm training a model to classify whether a person is smiling (showing teeth) or not. I'm using Keras and I trained a VGG16 model loaded with the ImageNet weights, froze the first 4 layers and added a ...
0
votes
1answer
21 views

How do we call when one model is trained by another?

Suppose I have one model (say, for image classification) as black box. I don't posess it and don't know it's parameters. Suppose it is web API. Then I take bunch of images, classify them by this ...
-1
votes
2answers
46 views

Transfer learning scenario [closed]

I have an interesting question and I need some help. Consider the following problem. Let's suppose that I am doing regression with neural networks. As input I have a set of measurements, arrays of $N$ ...
1
vote
0answers
174 views

Transfer Learning for Multivariate Regression

As I understand it, transfer learning is termed as using the parameters of a pre-trained model, which was initially trained on a particular 'source' task, and have it train on another related 'target' ...
0
votes
1answer
434 views

Transfer learning for audio

I know that when working with images, what people normally do is download a big model trained with huge data and freeze most of the layers except the lasts ones to train them with their own data. I'm ...
6
votes
1answer
2k views

Transfer learning: How and why retrain only final layers of a network?

In this video, Prof. Andrew Ng says regarding transfer learning: Depending on how much data you have, you might just retrain the new layers of the network, or maybe you could retrain even more ...