Questions tagged [convolutional-neural-networks]

For questions about convolutional neural networks, also known as CNN or ConvNet.

Filter by
Sorted by
Tagged with
23
votes
3answers
38k views

How do I handle large images when training a CNN?

Suppose that I have 10K images of sizes $2400 \times 2400$ to train a CNN. How do I handle such large image sizes without downsampling? Here are a few more specific questions. Are there any ...
1
vote
0answers
18 views

How to use K-means clustering to visualise learnt features of a CNN model?

Recently, I was going through the paper Intriguing Properties of Contrastive Losses. In the paper (section 3.2), the authors try to determine how well the SimCLR framework has allowed the ResNet50 ...
0
votes
0answers
12 views

Improve generalization of phishing website detection with computer vision

I want to use computer vision to detect phishing websites. There has already been some study on this, which showed this is effective. Most phishing sites try to replicate well-known websites such as ...
1
vote
1answer
20 views

When is an object detection approach over a CNN approach appropriate?

I understand that CNNs are for image classification while object detection is for localization + classification of the objects detected. However, in particular, AI for chest radiographs, why is object ...
2
votes
1answer
77 views

Is my fine-tuned model learning anything at all?

I am practicing with Resnet50 fine-tuning for a binary classification task. Here is my code snippet. ...
0
votes
1answer
23 views

A neural network to learn the connection between two totally different type of images

I have a dataset of two different type of images. Say, I have images of a person and his all 10 fingerprints. I want to create a relation between them to predict one from another. How I can do that ...
0
votes
0answers
34 views

Hand Landmark Detector Not Converging

I'm currently trying to train a custom model with TensorFlow to detect 17 landmarks/keypoints on each of 2 hands shown in an image (fingertips, first knuckles, bottom knuckles, wrist, and palm), for ...
1
vote
1answer
58 views

YOLOv3 Synthetic Data Training

Suppose we want to train a model to detect various objects. Let's say we have training data of those objects in various backgrounds along with their bounding boxes. Basically these objects have been ...
1
vote
1answer
89 views

Why do the training and validation loss curves differge?

I was training a CNN model on TensorFlow. After a while I came back and saw this loss curve: The green curve is training loss and the gray one is validation loss. I know that before epoch 394 the ...
0
votes
0answers
19 views

pytorch TypeError: forward() takes 1 positional argument but 2 were given [closed]

I have been trying to implement a small VGG network but run into this error. Here is the error message I am getting: ...
2
votes
1answer
94 views

What is the difference between FC and MLP in as used in PointNet?

I am trying to understand the PointNet network for dealing with point clouds and struggling with understanding the difference between FC and MLP: "FC is fully connected layer operating on each ...
3
votes
1answer
283 views

When training a CNN, what are the hyperparameters to tune first?

I am training a convolutional neural network for object detection. Apart from the learning rate, what are the other hyperparameters that I should tune? And in what order of importance? Besides, I read ...
1
vote
1answer
32 views

Is there any recommended way to perform pooling in this context?

Suppose I have three batches of feature maps, each of size $180 \times 100 \times 100$. I want to concatenate all these feature maps channel-wise, and then resize them into a single feature map. The ...
4
votes
2answers
249 views

Can neurons in MLP and filters in CNN be compared?

I know they are not the same in working, but an input layer sends the input to $n$ neurons with a set of weights, based on these weights and the activation layer, it produces an output that can be fed ...
12
votes
1answer
4k views

What is the difference between a receptive field and a feature map?

In a CNN, the receptive field is the portion of the image used to compute the filter's output. But one filter's output (which is also called a "feature map") is the next filter's input. What's the ...
2
votes
2answers
32 views

Improving validation losses and accuracy for 3D CNN

I have used a 3D CNN architecture, for detecting the presence of a particular promoter (MGMT), by using FLAIR brain scans. (64 slices per patient). The output is supposed to be binary (0/1). I have ...
2
votes
1answer
85 views

How do I choose the hyper-parameters for a model to detect different guitar chords?

I need to build a hand detector that recognizes the chord played by a hand on a guitar. I read this article Static Hand Gesture Recognition using Convolutional Neural Network with Data Augmentation ...
1
vote
1answer
47 views

If I wanted to calculate multiple feature maps in a convolutional layer, should the filters be trained individually?

Assume I have an input of size $32 \times 32 \times 3$ and pass it to a convolution layer. Now, if my kernel size were to be $5 \times 5 \times 3$ and the depth of my convolution layer were to be 1, ...
1
vote
1answer
60 views

How to construct input dependent convolutional filter?

I am constructing a convolutional variational autoencoder for images, starting out with mnist digits. Typically I would specify convolutional layers in the following way: ...
0
votes
1answer
43 views

Best Camera and protocol for embedded real time CNN project

I'm looking to develop a stand-alone real-time outdoor imaging CNN application, and I can't wrap my head around the myriad of camera options and their communication protocols. The target is a Linux ...
0
votes
1answer
22 views

Validation accuracy less than training accuracy (with no sigh of overtraining)

I am working with a deep CNN with over 100k sample data. I divided it up into 75% training, 12.5% validation and 12.5% for testing. As I train my network, the training accuracy approaches near 100% ...
7
votes
3answers
4k views

How can 3 same size CNN layers in different ordering output different receptive field from the input layer?

Below is a quote from CS231n: Prefer a stack of small filter CONV to one large receptive field CONV layer. Suppose that you stack three 3x3 CONV layers on top of each other (with non-linearities in ...
1
vote
2answers
73 views

What do people refer to when they use the word 'dimensionality' in the context of convolutional layer?

In practical applications, we generally talk about three types of convolution layers: 1-dimensional convolution, 2-dimensional convolution, and 3-dimensional convolution. Most popular packages like ...
1
vote
1answer
57 views

Why do we add 1 in the formula to calculate the shape of the output of the convolution?

In the formula to calculate output shape of tensor after convolution operation $$ W_2 = (W_1-F+2P)/S + 1, $$ where: $W_2$ is the output shape of the tensor $W_1$ is the input shape $F$ is the filter ...
4
votes
3answers
1k views

How is the depth of the input related to the depth of the output of a convolutional layer?

Let's suppose I have an image with 16 channels that goes to a convolutional layer, which has 3 trainable $7 \times 7$ filters, so the output of this layer has depth 3. How does the convolutional layer ...
1
vote
1answer
70 views

How can max-pooling be applied to find features in words?

I'm reading about max-pooling in a dynamic CNN paper. I can see how it can help find features in images, given that the pixel with the highest density gets pooled, but how does it help to find ...
34
votes
6answers
10k views

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document. I want the CNN to report errors, so I ...
1
vote
0answers
17 views

What is meant by "spatial encoding" in the context of convolutional neural networks?

Consider the following excerpt from the abstract of the research paper titled Squeeze-and-Excitation networks by Jie Hu et al. Convolutional neural networks are built upon the convolution operation, ...
2
votes
1answer
899 views

Are mult-adds and FLOPs equivalent?

I am comparing different CNN architectures for edge implementation. Some papers describing architectures refer to mult-adds, like the MobileNet V1 paper, where it is claimed that this net has 569M ...
1
vote
1answer
20 views

How to embed game grid state with walls as an input to neural network

I've read most of the posts on here regarding this subject, however most of them deal with gameboards where there are two different categories of single pieces on a board without walls etc. My game ...
7
votes
2answers
150 views

CNNs: What happens from one neuron volume to the next?

I've gone through several descriptions of CNNs online and they all leave out a crucial part as if it were trivial. A "volume" of neurons consists of several parallel layers ("feature ...
0
votes
0answers
35 views

How does bipartite matching work in DETR?

I was going through the DETR paper to understand this end-to-end detection transformer used for object detection, and I came across this bipartite matching thing.
0
votes
1answer
23 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 ...
1
vote
1answer
27 views

Is it possible to have different channel dimensions in a CNN?

Let's say I have two channels that I wish to feed into a CNN. One of the channel contains 4 traces and has a width of 512. Stacking them on top of each other therefore yields an image with dimensions (...
3
votes
0answers
75 views

What are the purposes of pooling in CNNs?

There are at least three questions on this site related to this What is the effect of using pooling layers in CNNs? Is pooling a kind of dropout? What are the benefits of using max-pooling in ...
0
votes
2answers
50 views

Correctly input additional values into CNN

I understand that in order to add additional inputs to a CNN, e.g. in self driving, I can append the data to a flattened layer after the convolutions and before the fully connected layers. However, a ...
3
votes
1answer
2k views

How are the kernels initialized in a convolutional neural network?

I am currently learning about CNNs. I am confused about how filters (aka kernels) are initialized. Suppose that we have a $3 \times 3$ kernel. How are the values of this filter initialized before ...
-1
votes
1answer
24 views

What practically makes a good architecture of ANN?

When we take a look at the literature there are so many opinions. I was wondering what are some generally good practices to design an architecture, like how much depth would you prefer and how much ...
2
votes
2answers
59 views

How general is generalization?

I am sorry but I have to explain my question using an example, I do not know how to ask it in proper scientific terms. Let's assume, I have trained a deep learning model on classifying hand gestures, ...
3
votes
1answer
383 views

Why would we use attention in convolutional neural networks, and how would we apply it?

Attention has been used widely in recurrent networks to weight feature representations learned by the model. This is not a trivial task since recurrent networks have a hidden state that captures ...
1
vote
1answer
75 views

Explanation of this L2 minimization equation

I am trying to understand the last two lines of this math notation (from this paper). How did Var and double summation of Cov come to the equation? The first two lines I understood something like $(a-...
1
vote
1answer
29 views

How do you handle unbalanced image datasets?

I have an image data set on which I am training a CNN. The data set is slightly unbalanced. So, my solution up till now was to delete some images of the majority class. But I now realize that there ...
2
votes
1answer
30 views

Is it true that channels always represent colours of an image?

Convolutional neural networks are widely used in image-related tasks in artificial intelligence. The input of a conventional neural network is generally an image. The output of a convolutional neural ...
3
votes
1answer
130 views

What's the difference between architectures and backbones?

In the paper "ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery", the authors talk about using: Feature Pyramid Networks (as the ...
2
votes
2answers
148 views

Which neuron represents which part of the input?

In a neural network, each neuron represents some part of the input. For example, in the case of a MNIST digit, consider the stem of the number 9. Each neuron in the NN represents some part of this ...
0
votes
0answers
13 views

Brain tumour detection using CNN

I have a fairly basic mathematical and implementational understanding of ML algorithms and CNNs, and I am trying to think of an approach for this task: https://www.kaggle.com/c/rsna-miccai-brain-tumor-...
1
vote
1answer
377 views

In Faster R-CNN, how can I get the predicted bounding box given the neural network's output?

The RPN loss in Faster RCNN paper is $$ L({p_i}, {t_i}) = \frac{1}{N_{cls}} \sum_{i} L_{cls}(p_i,p_i^*) + \lambda \frac{1}{N_{reg}} \sum_i p_i^* L_{reg}(t_i, t_i^*) $$ For regression problems, we have ...
0
votes
0answers
12 views

Counting number of coaches in a train from real time video feed

I have a real time video feed of a train platform. I was able to detect coaches using CNN based model. But how can I calculate number of coaches in the train that passed the platform as well as the ...
7
votes
4answers
2k views

Why is my test error lower than the training error?

I am trying to train a CNN regression model using the ADAM optimizer, dropout and weight decay. My test accuracy is better than training accuracy. But, as far as I know, usually, the training accuracy ...
0
votes
1answer
27 views

What is meant by "shorter connections" in the case of deep convolutional neural networks?

Consider the following two excerpts from the research paper titled Densely Connected Convolutional Networks by Gao Huang et al. #1: From abstract Recent work has shown that convolutional networks can ...

1
2 3 4 5
21