Questions tagged [convolutional-neural-networks]

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

340 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
5
votes
0answers
28 views

What is the point of using convolutions of kernel size 1, or 1x1, etc?

I understand the gist of what convolutional networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel ...
5
votes
1answer
197 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....
5
votes
1answer
217 views

Other Deep Learning Networks for Visual Place Recognition?

I am doing a project on Visual Place Recognition in Changing Environments. The CNN used here is mostly AlexNet, and a feature vector is constructed from Layer 3. Does anyone know of similar work ...
5
votes
1answer
778 views

What to do if CNN cannot overfit a training set on adding dropout?

I have been trying to use CNN for a regression problem. I followed the standard recommendation of disabling dropout and overfitting a small training set prior to trying for generalization. With a 10 ...
4
votes
0answers
64 views

What should I do with the flatten layer during back-propagation?

I'm creating a CNN network without other frameworks such as PyTorch, Keras, Tensorflow, and so on. During the forward pass, the Flatten layer reshapes the previous ...
4
votes
0answers
139 views

Get the position of an object, out of an image

I have some images with a fixed background and a single object on them which is placed, in each image, at a different position on that background. I want to find a way to extract, in an unsupervised ...
4
votes
0answers
26 views

What are some neural network models that can use auxiliary info during training for image segmentation?

What are some deep learning models that can use supplementary information other than RGB channels for image segmentation? For example imagine a poorly shot image of a river (blue) that shows a gap, ...
4
votes
0answers
41 views

How do I denoize a microscopic image?

I'm working in a computer vision project, where the goal is to detect some specific parasites, but now that I have the images, I noticed that they have a watermark that specifies the microscope ...
4
votes
2answers
2k views

What is the purpose of “reshaping it into the shape the network expects and scaling it so that all values are in the [0, 1] interval.”?

I am a deep learning beginner recently reading this book "Deep learning with Python", the example explains the process of implementing a greyscale image classification using MNIST in keras, in the ...
4
votes
1answer
120 views

Is one big network faster than several small ones?

The basis of my question is that a CNN that does great on MNIST is far smaller than a CNN that does great on ImageNet. Clearly, as the number of potential target classes increases, along with image ...
4
votes
0answers
148 views

Game AI - Modify image classification model for analog output

I'm developing a Game AI which tries to master racing simulation. I already trained a CNN (alexnet) on ingame footage of me playing the game and the pressed keys as the target. I had two main issues ...
4
votes
0answers
157 views

How to feed a variable size sequences into a CNN?

If I want to train a convoluted NN on time series but I cannot decide where to split the data. I see that other people use jumping window over the input. so the feed say 20 sec of observation as 1 ...
4
votes
1answer
57 views

GPU/TPU acceleration for neural networks with various network topologies

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
3
votes
0answers
23 views

Conversion of strided filter gradient to convolutional form

I'm implementing strided 2D convolution. My formula looks like this: $$y_{i, j} = \sum_{m=0}^{F_h - 1}\sum_{n=0}^{F_w - 1} x_{s\cdot i + m, s\cdot j + n}\,f_{m, n}, \tag{1}$$ where $s$ is the stride (...
3
votes
0answers
135 views

Understanding the results of “Visualizing and Understanding Convolutional Networks”

I am trying to understand the results of the paper Visualizing and Understanding Convolutional Networks, in particular the following image: What are these 3x3 blocks and their 9 cells representing? ...
3
votes
0answers
35 views

How to predict an event (or action) based on a window of time-series measurements?

I have an input vector $X$, which contains a series of measurements within a period, e.g. 100 measurements in 1 sec. The goal is to predict an event, let's say, moving forward, backward or static. I ...
3
votes
1answer
50 views

How to solve the problem of variable-sized AST as input for a (convolutional) neural network model?

In my work I have a given source code for a module. From this module I generate an AST, whose size is dependent on the size of the module (e.g. more source code -> bigger AST). I want to train a ...
3
votes
0answers
39 views

What are some ways to quickly evaluate the potential of a given NN architecture?

Main question Is there some way we can leverage general knowledge of how certain hyperparameters affect performance, to very rapidly get some sort of estimate for how good a given architecture could ...
3
votes
0answers
39 views

How can I do hyperparameter optimization for a CNN-LSTM neural network?

I have built a CNN-LSTM neural network with 2 inputs and 2 outputs in Keras. I trained the network with model.fit_generator() (and not ...
3
votes
1answer
49 views

How to draw bounding boxes for gender classification?

I wonder what is the better way of drawing rectangles on images for gender classification. My task is to create a classifier (CNN based) to detect gender from pictures of entire bodies (not just faces)...
3
votes
2answers
59 views

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
3
votes
0answers
16 views

Size of image input of neural networks while resizing may not be appropriate

I have the following problem while using convolutional neural networks to detect forgeries: Resizing the image to fit the required input size may not be a good way because the forgery detection ...
3
votes
0answers
50 views

Ideas on a network that can translate image differences into motor commands?

I'd like to design a network that gets two images (an image under construction, and an ideal image), and has to come up with an action vector for a simple motor command which would augment the image ...
3
votes
1answer
187 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 ...
3
votes
0answers
30 views

How do we give a kick start to the Facenet network?

I read the Facenet paper and one thing I am not sure about (it might be trivial and I missed it) is how do we give the kick start to the network. The embeddings in the beginning are random, so ...
3
votes
0answers
27 views

Training a reinforcement learning model with multiple images

I am tentatively trying to train a deep reinforcement learning model the maze escaping task, and each time it takes one image as the input (e.g., a different "maze"). Suppose I have about $10K$ ...
3
votes
0answers
52 views

How to train CNN such it eliminate dependent features and focuses on independent ones?

How we should train a CNN model when training dataset contains only limited number of cases, and the trained model is supposed to predict class (label) for several other cases, which has not seen ...
3
votes
0answers
44 views

What is meant by “model discriminability for local patches within the receptive field”?

In the Abstract section of the paper Network In Network, what does the authors actually mean to say?
3
votes
0answers
622 views

How to calculate gradient of filter in convolution network

I have similar architecture like in image:CNN. I don't understand how to calculate gradient of filter F. I found these equations(source): Gradient and delta, where first equation calculate gradient ...
3
votes
1answer
203 views

What are the differences between Bytenet and Wavenet?

I recently read Bytenet and Wavenet and I was curious why the first model is not as popular as the second. From my understanding, Bytenet can be seen as a seq2seq model where the encoder and the ...
2
votes
0answers
23 views

Structure-preserving layer in a network with respect to a transformation

I'm reading this paper: https://arxiv.org/pdf/1602.07576.pdf. I'll quote the relevant bits: Deep neural networks produce a sequence of progressively more abstract representations by mapping the input ...
2
votes
1answer
45 views

Is it possible to apply the associative property of the convolution operation when it is followed by a non-linearity?

The associative property of multidimensional discrete convolution says that: $$Y=(x \circledast h_1) \circledast h_2=x\circledast(h_1\circledast h_2)$$ where $h_1$ and $h_2$ are the filters and $x$ is ...
2
votes
0answers
26 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 (...
2
votes
0answers
27 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
27 views

Merge two different CNN models into one

I have 2 different models with each model doing a separate function and have been trained with different weights. Is there any way I can merge these two models to get a single model. If it can be ...
2
votes
1answer
65 views

Can you explain me this CNN architecture?

I am starting to get my head around convolutional neural networks, and I have been working with the CIFAR-10 dataset and some research papers that used it. In one of these papers, they mention a ...
2
votes
0answers
23 views

How should I define the loss function for a multi-object detection problem?

I'm trying to create a text recognition project using CNN. I need help regarding the text detection task. I have the training images and bounding box details for them. But I'm unable to figure out ...
2
votes
1answer
48 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 ...
2
votes
0answers
36 views

Creating Dataset for Image Classification

I want to develop a CNN model to identify 24 hand signs in American Sign Language. I created a custom dataset that contains 3000 images for each hand sign i.e. 72000 images in the entire dataset. For ...
2
votes
1answer
225 views

What are some good alternatives to U-Net for biomedical image segmentation?

Soon I will be working on biomedical image segmentation (microscopy images). There will be a small amount of data (a few dozens at best). Is there a neural network, that can compete with U-Net, in ...
2
votes
0answers
22 views

What is the difference between training a model with RGB images and using only the color channels separately?

What is the difference between training a model with RGB images and using only the color channels separately (like only the red channel, green channel, etc.)? Would the model also learn patterns ...
2
votes
0answers
102 views

Adding a dense layer after a conv2d layer in a convolutional autoencoder

I am trying to implement a convolutional autoencoder with a dense layer at the bottleneck do to some dimensional reduction. I have seen two approaches for this which arent particularly scalable. The ...
2
votes
1answer
68 views

Can a fully convolutional network always return an image of the same size as the original?

I'm trying to perform a segmentation task on images of multiple sizes using fully convolutional neural networks. Currently, I'm using EfficientNet as a feature extractor, and adding a deconvolution/...
2
votes
0answers
34 views

Why does model complexity increase my validation score by a lot?

I learned that when creating neural networks the go to was to overfit and then to regularize. However I am now in a situation where, when I make the model more complex (more layers, more filters, ...) ...
2
votes
0answers
31 views

Is there an efficient way of determining the layers with the best performance as feature extractors in GoogleNet?

I am using a caffe model of pre-trained GoogleNet trained on ImageNet from here for image retrieval task (place recognition, more specifically). I would like to know the layer with best performance ...
2
votes
0answers
45 views

Is there a way to add “focus” on parts of the image when using CNNs?

I'm building a CNN/3DCNN model that classifies hand gestures. The problem is that the actual gesture occupies only like 1% of the whole image. That means that an enormous amount of convolutional ...
2
votes
2answers
59 views

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling?

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling? If not, why do they perform as well as networks which use max-pooling?
2
votes
0answers
19 views

Why is the loss of one of the outputs of a model with multiple outputs increasing while the others are decreasing?

I'm a newbie in neural networks. I'm trying to fit my neural network that has 3 different outputs: semantic segmentation, box mask and box coordinates. When my model is training, the loss of ...
2
votes
0answers
40 views

Why does the BatchNormalization layer produce different outputs during training and inference?

I modified resnet50 architecture to get a regression network. I just add batchnorm1d and ReLU layers just before the fully connected layer. During the training, the output of batchnorm1d layer is ...
2
votes
0answers
62 views

What is the difference between using a backbone architecture and transfer learning?

I'm super new to deep learning and computer vision, so this question may sound dumb. In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (e.g., ...

1
2 3 4 5
7