Questions tagged [convolutional-neural-networks]

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

194 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
11
votes
3answers
956 views

What topologies are largely unexplored in machine learning?

Geometry and AI Matrices, cubes, layers, stacks, and hierarchies are what we could accurately call topologies. Consider topology in this context the higher level geometrical design of a learning ...
5
votes
2answers
621 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
35 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
2answers
148 views

What is the difference between graph convolution in the spatial vs spectral domain?

I've been reading different papers regarding graph convolution and it seems that they come into two flavors: spatial and spectral. From what I can see the main difference between the two approaches is ...
4
votes
0answers
39 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
1answer
101 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....
4
votes
1answer
193 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 ...
4
votes
0answers
142 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
151 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 ...
3
votes
0answers
21 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
0answers
77 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
15 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, ...
3
votes
0answers
18 views

What parameters can be tweaked to avoid a generator or discriminator loss collapsing to zero when training a DC-GAN?

Sometimes when I am training a DC-GAN on an image dataset, similar to the DC-GAN PyTorch example (https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html), either the Generator or ...
3
votes
0answers
29 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
49 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
2answers
1k 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 ...
3
votes
0answers
505 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
48 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, ...
2
votes
0answers
26 views

How should I handle different input sizes in graph convolution networks?

I'm a student beginning to study deep learning, and would like to practice with a simple project using a Graph Convolutional Network. However, I'm not quite sure how to handle different input sizes ...
2
votes
0answers
18 views

How can I train YOLO with the COCO dataset?

I am trying to implement the original YOLO architecture for object detection, but I am using the COCO dataset. However, I am a bit confused about the image sizes of COCO. The original YOLO was trained ...
2
votes
1answer
35 views

How GoogleNet actually deal with reducing overfitting?

Today I was going through a tutorial of Andrew Ng about Inception network. He said that GoogLeNet's hidden layers are also good in prediction and it had somehow a regularization effect, so it reduces ...
2
votes
0answers
29 views

Difference in the code structure of RNN and CNN

I understand that in general RNN is good for time series data and CNN image data, and have noticed many blogs explaining the ...
2
votes
0answers
26 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, ...
2
votes
0answers
12 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 ...
2
votes
0answers
13 views

How to properly use batch normalization during inference

I am trying to manually implement calculations of the image classification process using pre-trained weights from the MobilenetV2 network. I know how to apply filter weights to the channels, but not ...
2
votes
0answers
20 views

Which neural network algorithms can be used to map motion vectors in image processing?

I'm working on finding out the motion vectors of objects in images. The inputs are the images of objects in motion. The outputs of neural network are the object name, direction of object vector and ...
2
votes
0answers
41 views

CNN clasification model loss stuck at same value

I have CNN model to classify 2 classes. (Yes or No) I use categorical_crossentropy loss and softmax activation at the end. For input I use image with all 3 channels, for output I use One hot encoded ...
2
votes
0answers
20 views

Confidence Maps and Non-Linearity

I am currently trying to improve a CNN architecture that was proposed for generating depth images. The architecture was originally proposed for autonomous driving and it looks like following : The ...
2
votes
0answers
47 views

Torch CNN not training

I am completely new to CNN's, and I do not quite know how to design or use them efficiently. That being said, I am attempting to build a CNN that learns to play Pac-man with reinforcement learning. I ...
2
votes
0answers
28 views

3D geometry and similarity with a reference model

I am looking for a CNN method, or any other machine learning method, to recognize 3D natural geometries that are similar to each others, and compare these geometries with a reference 3D model. To ...
2
votes
0answers
23 views

What is the difference between Squeeze-and-excite and bottleneck modules from Mobilenet v2?

Squezee-and-excite networks introduced SE blocks, while MobileNet v2 introduced linear bottlenecks. What is the effective difference between these two concepts? Is it only implementation (depth-wise ...
2
votes
0answers
30 views

Pipeline to Estimate Measurement of Human Body Point Cloud

I am developing a Body Measurement extraction application, my current stage is able to extract the point clouds of human body in a standing posture, from every angles. Now, to be able to recognize ...
2
votes
0answers
39 views

Understanding CNN+LSTM concept with attention and need help

I have a question about the context of CNN and LSTM. I have trained a CNN network for image classification. However, I would like to combine it with LSTM for visualizing the attention weights. So, I ...
2
votes
0answers
56 views

Why is graph convolution network in time-varying graphs useful for anomaly detection?

In this paper, the authors refer to the application of time-varying graphs as an open problem. And they say it will be useful for anomaly detection in financial networks, etc. But why is that useful?
2
votes
0answers
23 views

How to voxelize multiple frames at the time and append them together?

I'm trying to implement this approach for object detection and tracking. In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels ...
2
votes
0answers
31 views

How is the bias caused by a max pooling layer overcome?

I have constructed a CNN that utilizes max-pooling layers. I have found with these layers that, should I remove them, my network performs ideally with every output and gradient at each layer having a ...
2
votes
0answers
34 views

Can GANs be used to generate matching pairs to inputs?

I have some limited experience with MLPs and CNNs. I am working on a project where I've used a CNN to classify "images" into two classes, 0 and 1. I say "images" as they are not actually images in the ...
2
votes
0answers
37 views

Object size identification and maximum number of classes with convolutional neural networks

I am working on a project that involves using a ConvNet to identify screws. I am able to train from scratch a ConvNet based on the first version of the inception network, but shallower (only 3 ...
2
votes
0answers
23 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 $10K$ ...
2
votes
0answers
11 views

How to debug and find neurons that most influenced a pixel in the output image?

I'm building CNN network of Image to Image. After training, I have some bad results in part of the Image. I would like to find the neurons that most influenced those pixels and do retraining only ...
2
votes
0answers
40 views

Algorithms to indentify people in pictures without using face recognition

There are lot of researches about face detection in pictures, but is it the only way one can say "this person I'm looking for is here in this picture"? Aren't there algorithms that you can provide ...
2
votes
0answers
97 views

Convolutional Sequence to Sequence Learning: Training vs Generation

I am struggling to understand the use of the Convolutional Sequence to Sequence (Conv-Seq2Seq) model. The image below is take directly from the paper and is the nearly canonical diagram of the ...
2
votes
0answers
28 views

Is making lot of 1 versus other model efficient?

I've got classification problem on image, I have 10 classes and when I fine tuned my model on it (I tried VGG, Xception, resnet etc) I have approximatly 83% validation accuracy. I was wondering if ...
2
votes
0answers
41 views

How can the convolution operation be implemented as a matrix-vector multiplication?

How can the convolution operation used by CNNs be implemented as a matrix-vector multiplication? We often think of the convolution operation in CNNs as a kernel that slides across the input. However, ...
2
votes
0answers
24 views

Calculating tangent vector of curve s(P,$\alpha$) at given point $\alpha$ = 0

I am reading the paper "Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation", where the tangent vector is calculated for the given curve $s(P,\alpha)$ at $\...
2
votes
2answers
77 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
0answers
33 views

How does a neural network output text box location data?

I'm interested in creating a convolutional neural network or LSTM to locate text in an image. I don't want to OCR the text yet, just find the text regions. Yes, I know Tesseract and other systems can ...
2
votes
0answers
145 views

How does DARTS compare to ENAS?

How does DARTS compare to ENAS? Which one is better or what advantages does they each have? Links: DARTS: Differentiable Architecture Search Efficient Neural Architecture Search via Parameter ...
2
votes
0answers
44 views

How a game playing agent could identify potential objects and proximity?

Most implementations I'm seeing for playing games like Atari (usually similar to DeepMind's work using DQN) have 4 graphical frames of input fed into 3 convolutional layers which are then fed into a ...
2
votes
1answer
447 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 ...