Questions tagged [multiclass-classification]

In machine learning, multiclass or multinomial classification is the problem of classifying instances into one of three or more classes (classifying instances into one of two classes is called binary classification).

Filter by
Sorted by
Tagged with
2 votes
1 answer
101 views

Image classification problem with multiple right classes

I have a use case where the model needs to detect fabricdefects. There are 15+ different kinds of defects. In one image there can be multiple defects present. The straight forward solution for this ...
0 votes
0 answers
18 views

How to train a N binary classifier with shared encoder as replacement of multiclass classifier?

all I have data for 3 categories (positive and negative category). For my solution, I can build a multiclass classifier with 4 classes (positive data from each category and negative data combined ...
0 votes
0 answers
34 views

How to add pretrained vectorizer and classification model to onnx pipeline for NLP task?

I have trained Logistic regression model for documents classification. I have saved the fit tfidf vectorizer and the model as well. Also, I have created a custom DataCleaner class which inherits ...
  • 101
2 votes
0 answers
25 views

Which algorithm for hierarchical and ordered classification? [closed]

I have developed the "Pyrates" application which is a serious game to learn programming in Python. In each level of the game, you have to pick up a key and open a chest. To do this, you need ...
1 vote
0 answers
155 views

Out of distribution detection (OOD) in the context of regression problems

I'm working in a regression setting to predict a scalar value $y$ from an input $\textbf{x} \in \mathbb{R}^D$ and I'm interested in understanding whenever my model is fed with something that it is ...
0 votes
0 answers
30 views

Derivation of the sparsemax loss function

While reading this interesting paper about a sparse variant of the reknown softmax activation function, I got stuck at the section about loss derivation. In particular, I'm having issues understanding ...
0 votes
0 answers
28 views

What are some of the commonly used image processing techniques of OpenCV for multiclass image classification?

I'm working on multiclass skin disease image classification(caused by bacteria and fungus). Some of the sample images are shown below. Images contain different background as shown in image_1 and ...
  • 1
0 votes
1 answer
351 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 ...
  • 101
0 votes
1 answer
102 views

Multiclass Ensemble Methods with weak classifiers under 50%

Normally, when using an ensemble method, such as baggin or boosting, in binary classification, there is a reqauirment that each weak classifier have accuracy better than 50%. In the multiclass ...
-1 votes
1 answer
690 views

Low accuracy and high loss in multi-class classification [closed]

I'm trying to classify images in 17 flowers dataset which consist of 1360 images of 17 classes (80 images per class); I have to use DNNs only therefore I made my model with the following settings: <...
1 vote
0 answers
82 views

Use soft-max post-training for a ReLU trained network?

For a project, I've trained multiple networks for multiclass classification all ending with a ReLU activation at the output. Now the output logits are not probabilities. Is it valid to get the ...
0 votes
1 answer
207 views

How to label unsupervised data for deep learning multi-classification

I have unlabeled credit card transaction data that has the following columns: ...
0 votes
1 answer
79 views

Multi-class classification but a single feature sometimes boils it down to a binary-classification

I have a three-class classification problem for a large dataset. Classes are 0, 1, and 2. There's a categorical variable in my feature vectors such that when a sample point has this variable positive, ...
  • 1
0 votes
1 answer
470 views

When to use Multi-class CNN vs. one-class CNN

I'm building an object detection model with convolutional neural networks (CNN) and I started to wonder when should one use either multi-class CNN or a single-class CNN. That is, if I'm making e.g. a ...
  • 111
0 votes
1 answer
115 views

How do I select the class weights for the loss function in the case of more than 2 classes?

I have a machine learning task where I would like to weight losses based on the frequency of the categorical values appearing in the data. The binary solution can be seen below, but I'd like to know ...
0 votes
1 answer
79 views

Why would the "improvement" be the result of random initialization, and so why should we use multiple runs?

I got this feedback for my thesis paper. The improvement shown in the results section could be the result of random initialization. There should be multiple runs with means and standard deviations. ...
1 vote
0 answers
80 views

How to deal with images that do not contain any object of interest?

I'm currently working on an iOS App where I want to detect if there is a table, chair or bench in the current camera input. My idea was to take the MobileNetV2 model and get it to classify these three ...
  • 11
1 vote
2 answers
844 views

What is the difference (if any) between semantic segmentation and multi-class, mutually exclusive classification?

Multi-class classification is simply assigning all data points into one of up to any finite number of mutually exclusive labels. I am new to the field(s) of AI/ML and I keep hearing people use the ...
0 votes
1 answer
104 views

How to perform multi-class text classification with a dataset of 80 documents?

I have a training dataset of 80 text documents with an average number of characters in each document of 25000 and 210 unique tags. How can I perform multi-class text classification with such a small ...
2 votes
1 answer
2k views

Why do we use the softmax instead of no activation function?

Why do we use the softmax activation function on the last layer? Suppose $i$ is the index that has the highest value (in the case when we don't use softmax at all). If we use softmax and take $i$th ...
1 vote
1 answer
6k views

How do I calculate the probabilities of the BERT model prediction logits?

I might be getting this completely wrong, but please let me first try to explain what I need, and then what's wrong. I have a classification task. The training data has 50 different labels. The ...
  • 113
1 vote
0 answers
25 views

Using one-class classification first to find anomalies then apply multi-class classification

I'm new to machine learning and trying to apply it for fault detection, an idea came to mind which is using only anomaly detection after which if the results after a while come up as positive, a multi-...
  • 11
1 vote
1 answer
174 views

Multi class text classification when having only one sample for classes

I have a dataset of texts, each text was identified with an ID number. I would like to do a prediction by finding the best match ID number for upcoming new texts. To use multi text classification, I ...
  • 11
4 votes
0 answers
433 views

When computing the ROC-AUC score for multi-class classification problems, when should we use One-vs-Rest and One-vs-One?

The sklearn's documentation of the method roc_auc_score states that the parameter multi_class can take the value ...
  • 151
2 votes
1 answer
790 views

Is Mask R-CNN suited to solve a multi-class classification problem where the classes are related?

I want to create a model to solve a multi-class classification problem. Here are more details about my problem. Every picture contains only one object The background is very simple All objects ...
1 vote
1 answer
211 views

Is it possible to combine k-fold cross-validation and oversampling for a multi-class text classification task with imbalanced data?

I am dealing with an intent classification task on an Italian customer service data set. I've more or less 1.5k sentences and 29 classes (imbalanced). According to the literature, a good choice is to ...
  • 65
0 votes
1 answer
99 views

How can I prevent the CNN from classifying a new input into one of the existing labels (it was trained with) when the input has a new different label? [duplicate]

I'm trying to perform image classification with a CNN. In my case, the inputs are the covers of 9 books, so there are 9 labels. I am using TensorFlow's Keras. If I pass a new input (that has a label ...
user avatar
3 votes
2 answers
2k views

What is the general procedure to use and train neural networks for multi-class classification?

I am very new to machine learning. I am following the course offered by Andrew Ng. I am very confused about how we train our neural network for multi-class classification. Let's say we have $K$ ...
19 votes
2 answers
12k views

How to implement an "unknown" class in multi-class classification with neural networks?

For example, I need to detect classes for MNIST data. But I want to have not 10 classes for digits, but also I want to have 11th class "not a digit", so that any letter, any other type of ...