Questions tagged [convolutional-neural-networks]

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

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

default or “unknown” class

Has anyone investigated ways to initialize a network so that everything is considered "unknown" at the start? When you consider the ways humans learn, if something doesn't fit a class well enough it ...
0
votes
1answer
18 views

How to use 'Canny/Watershed' algorithm's output as an input for Image Classification Model

I have a very silly problem in hand. I have implemented 2 methods which give me the mask to separate the objects from the background. What I get from one method is the object encapsulated in the red ...
2
votes
1answer
208 views

Is there a ReLU-like activation function that concatenates positive and negative values?

Is there a ReLU-like activation function that concatenates positive and negative values? What is its name? Apparently, it doubles the output dimension.
1
vote
1answer
28 views

Convolutional Sequence to Sequence Learning kernel parameters

I am reading the paper Convolutional Sequence to Sequence Learning by Facebook AI researchers and having trouble to understand how the dimensions of convolutional filters work here. Please take a look ...
0
votes
0answers
17 views

How can I build a model that replaces a feature of one image with another feature?

I would like to build a neural network (using TensorFlow) that is able to take two animals, and replace a feature in the second with one in the first. For example, if given a dog and cat, the cat's ...
0
votes
1answer
18 views

What is the difference between exhaustive nearest neighbor search and k-nearest neighbour search?

I have two lists of feature vectors calculated from pre-trained CNN for image retrieval task: Query: FV_Q and Reference FV_R. <...
0
votes
0answers
6 views

Identifying and Labeling multiple letters in image

While I attempt to learn AI/ML I have taken on the task to create a Boggle solver. The idea is that a system could take an image of a Boggle arrangement of letters and identify the letters (and the ...
2
votes
2answers
96 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 ...
2
votes
2answers
84 views

What is the reasoning behind the number of filters in the convolution layer?

Let's assume an extreme case in which the kernel of the convolution layer takes only values 0 or 1. To capture all possible patterns in input of $C$ number of channels, we need $2^{C*K_H*K_W}$ filters,...
0
votes
2answers
47 views

Backpropagation of neural nets with shared weight

I am trying to understand the mathematics behind the forward and backward propagation of neural nets. To make myself more comfortable, I am testing myself with an arbitrarily chosen neural network. ...
3
votes
2answers
140 views

What is the effect of using pooling layers in CNNs?

I know how pooling works, and what effect it has on the input dimensions - but I'm not sure why it's done in the first place. It'd be great if someone could provide some intuition behind it - while ...
1
vote
0answers
24 views

Which one is more important in case of different loss optimization algorithms, Speed or the Route?

We have different kinds of algorithms to optimize the loss like AdaGrad, SGD + Momentum, etc. Some are more commonly used than the others. In some algorithms, they usually range out before they ...
2
votes
1answer
60 views

What should load_mask() return if an image doesn't have any objects? (Mask RCNN)

I want to use Mask RCNN to do image segmentation. I need to override the load_mask function for the dataset class. I know this function should return mask tensors and class ids of objects in an image. ...
0
votes
1answer
32 views

Is it a good idea to overfit on a small part of your data for faster model convergence?

I working on a classification problem that needs to detect patterns on a time serie. Basically, there's a catch-all class that means "no pattern detected", the other are for the specific patterns. The ...
8
votes
2answers
155 views

Can machine learning algorithms be used to differentiate between small differences in details between images?

I was wondering if machine learning algorithms (CNNs?) can be used/trained to differentiate between small differences in details between images (such as slight differences in shades of red or other ...
3
votes
1answer
168 views

In which scenario would you want to have two adjacent pooling layers?

In which scenario, when assembling a CNN, would you want to have two adjacent pooling layers, without a convolutional layer in between?
3
votes
3answers
697 views

Neural Network for Optical Mark Recognition?

I've created a neural net using the ConvNetSharp library which has 3 fully connected hidden layers. The first having 35 neurons and the other two having 25 neurons each, each layer with a ReLU layer ...
1
vote
0answers
19 views

Deep learning techniques with time-fixed, time-dependent and imaging data

I have a question about the use of deep learning techniques with time-fixed features and images (setting 1) and time-dependent features (setting 2). (I am pretty new to the deep learning world so ...
4
votes
1answer
96 views

Disentangled VAE doesn't reconstruct accurate grids

I am trying to implement the disentangled VAE model according to this link. I want to understand the architecture of this model in order to customize it later. As infrastructure, I have a Linux kernel ...
2
votes
1answer
40 views

Recognising Noise in Simple Classification

I have created a classifier for some simple gestures using an input layer, a hidden layer with tanh activation and an output softmax layer. I'm also using the Adam optimiser. The network classifies ...
0
votes
1answer
46 views

What happens to the channels after the convolution layer?

I wonder what happens to the 'channels' dimension (usually 3 for RGB images) after the first convolution layer in CNNs? In books and other sources, it is always said that the depth of the output ...
0
votes
1answer
47 views

not sure if fine-tuned network is finely-tuned

I am practicing with Resnet50 fine tuning for binary classification task, here is my code snippet. ...
2
votes
1answer
40 views

How can I sample the output distribution multiple times when pruning the filters with reinforcement learning?

I was reading the paper Learning to Prune Filters in Convolutional Neural Networks, which is about pruning the CNN filters using reinforcement learning (policy gradient). The paper says that the input ...
3
votes
2answers
51 views

How to represent and work with the feature matrix for graph convolutional network (GCN) if the number of features for each node is different?

I have a question regarding features representation for graph convolutional neural network. For my case, all nodes have a different number of features, and for now, I don't really understand how ...
39
votes
8answers
32k views

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: input_channels, filter_height, filter_width, number_of_filters. Furthermore, it is my ...
33
votes
6answers
9k 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 ...
0
votes
0answers
20 views

Regularization to enforce feature learning

Is there any research into ways to enforce feature selection across classes by network structure? Given the number of parameters in NN, even convnets are prone to over fitting. I'm curious if there ...
1
vote
0answers
19 views

Banding artifacts in CNN

I was working on a CNN for HDR image generation from LDR images. I used an encoder-decoder architecture and merged the input with the decoder output. However I'm getting some banding artifacts in the ...
5
votes
1answer
174 views

What are the ways to calculate the error rate of a deep Convolutional Neural Network, when the network produces different results using the same data?

I am new to the object recognition community. Here I am asking about the broadly accepted ways to calculate the error rate of a deep CNN when the network produces different results using the same data....
3
votes
1answer
161 views

How can I incrementally train a Yolo model without catastrophic forgetting?

I have successfully trained a Yolo model to recognize k classes. Now I want to train by adding k+1 class to the pre-trained weights (k classes) without forgetting previous k classes. Ideally, I want ...
0
votes
0answers
30 views

How to improve recognition of distanced objects?

I am developing a model of object detection based on fast-rcnn architecture (transfer learning) in tensorflow object detection API. My problem is that created model happens to produce very good ...
3
votes
1answer
230 views

How can I reduce the GPU memory usage with large images?

I am trying to train a CNN-LSTM model. The size of my images is 640x640. I have a GTX 1080 ti 11GB. I am using Keras with the TensorFlow backend. Here is the model. ...
16
votes
3answers
26k 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 ...
2
votes
1answer
94 views

Why do we need convolutional neural networks instead of feed-forward neural networks?

Why do we need convolutional neural networks instead of feed-forward neural networks? What is the significance of a CNN? Even a feed-forward neural network will able to solve the image classification ...
3
votes
1answer
95 views

How do I calculate the partial derivative with respect to $x$?

I am trying to implement CNN using python Numpy. I searched so much, but all I found was for one filter with one channel for Convolution. Suppose we have an X as Image with this shape: ...
1
vote
0answers
18 views

How can I find the similar non-zero connections between different levels of sparsity of the same network?

I am pruning a neural network (CNN and Dense) and for different sparsity levels, I have different sub-networks. Say for sparsity levels of 20%, 40%, 60% and 80%, I have 4 different sub-networks. Now, ...
1
vote
1answer
38 views

Machine learning to find coordinate in image

I am trying to figure out how to approach this. Given training data of images and the pixel coordinates of the centre of an object in that image, would it be possible to predict the pixel coordinates ...
0
votes
0answers
9 views

Is there a difference between using 1d conv layers and 2d conv layers with kernel with size of 1 along other than time dimension?

Let's assume I use convolutional networks for time-series prediction. Data I feed to the network have 1 channel depth, height of number of periods and number of features is the width, so the frame ...
0
votes
1answer
23 views

What is the advantage of using Google's Coral over Nvidia's Xavier?

I was reading about the possibility of using Google's Coral for deep learning-based object detection and image classification. I heard it has a good speed in terms of frames/sec. I also read that ...
0
votes
0answers
10 views

How to set only the modified weights for each convolutional layers? [migrated]

I am currently doing some experiments on modifying the weights and not of the bias for each convolutional layers of a model. For each of the layers of the model, I used ...
2
votes
1answer
56 views

Is there a way that helps me to architect my CNN fundamentally before training?

While we train a CNN model we often experiment with the number of filters, the number of convolutional layers, FC layers, filter size, sometimes stride, activation function, etc. More often than not ...
8
votes
2answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and problem or domain-specific. However, there should be at least some "rules" that hold most times for the size of ...
11
votes
2answers
3k views

Which layer in a CNN consumes more training time: convolution layers or fully connected layers?

In a convolutional neural network, which layer consumes more training time: convolution layers or fully connected layers? We can take AlexNet architecture to understand this. I want to see the time ...
1
vote
0answers
20 views

How do we choose the filters for the convolutional layer of a convolution neural network?

Since the hidden layers of a CNN work as a trainable feature extractor, more detailed content based on a larger number of pixels shall require bigger filter sizes. But for cases where localized ...
2
votes
3answers
102 views

How do I determine which relevant features have been learned during training in a CNN?

Is there any way to control the extraction of features? How do I determine which features are been learned during training, i.e relevant information is been learned or not?
2
votes
0answers
20 views

How is visual attention mechanism different from a two branch convolutional neural network?

I am doing some research on the visual attention mechanism in remote sensing domain (where the features learnt from one layer are highlighted using the attention mask derived from another layer). From ...
2
votes
0answers
17 views

How does sampling works in case of imbalanced image datasets?

I am solving a problem of image classification of the image dataset for 3 classes. Dataset is highly imbalanced. How will sampling (either over- or under-sampling) work in that case? Should I remove (...
1
vote
0answers
8 views

How do CNNs or RNNs “stack the feature of nodes by a specific order”?

I am trying to understand the following statement taken from the paper Graph Neural Networks: A Review of Methods and Applications (2019). Standard neural networks like CNNs and RNNs cannot handle ...
1
vote
1answer
26 views

Heavily mixing signal differentiation from Open Set of backgrounds via CNN

To whomever can help out, I appreciate it. I am currently attempting to detect a signal from background noise. The signal is pretty well known but the background has a lotttt of variability. I've ...
1
vote
1answer
45 views

If features are always positives, why do we use RELU activation functions?

When does it happen that a layer (either first or hidden) outputs negative values in order to justify the use of RELU? As far as I know, features are never negative or converted to negative in any ...

1
2 3 4 5
15