Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
1
vote
0answers
4 views

Computational complexity of the forward pass of a CONVOLUTIONAL neural network?

How do I determine the computational complexity (big-O notation) of the forward pass of a CONVOLUTIONAL neural network? Let's assume for simplicity that we use zero-padding such that the input size ...
0
votes
0answers
12 views

Limbs for PAFs in OpenPose

What limbs are used in openpose for the PAF? If you look at the skeletal reconstruction one would assume it is $ears - eyes$, $eyes - nose$, $nose-neck$, $neck - hips$, $shoulders - elbows$, $elbows- ...
0
votes
0answers
16 views

Image classification on SVG format

To best of my knowledge, images are usually fed in pixel format to ML models. Is there any work that does image classification where the image format is SVG?
0
votes
0answers
12 views

Does the selective search algorithm in object detection learn?

I am trying to get a better grasp of how object detection works. I (almost) completely understand the concept behind RPNs. However I am little bit confused with the selective search algorithm part. ...
0
votes
0answers
13 views

Is RCNN resolution-independent, if keeping feature size constant?

From what I understand, (Faster/Mask-)RCNN is fully convolutional. The backbone is fully convolutional, and the region proposal network (RPN) creates anchors on the feature map with a fixed stride. ...
0
votes
0answers
22 views

Is Bayesian NN vs adding random data more accurate?

I’m trying to train a classifier to recognize if people are wearing seatbelts. What if the person submitted a picture unrelated to a seatbelt classifier? Would I create an image label that is full of ...
0
votes
0answers
17 views

The convolutional network architectures with enhanced invariance

It is well known, that CNN have advantage with respect to the Dense neural networks in the image classification and other pattern recognition tasks, because they have a translationall invariance built ...
0
votes
0answers
26 views

Since both RoI Align and PrRoI Pooling use bilinear interpolation, why is RoI Align discrete while PrRoI Pooling continuous?

I have two questions. Since both use bilinear interpolation, why is RoI Align discrete while PrRoI Pooling continuous? Could anyone explain the intuition behind the derivative of PrPool()?
0
votes
1answer
32 views

If I'm trying to build a binary image classifier, how do I handle images that aren't related to the classifier?

I am trying to create an image classifier to classify whether a person is wearing a seatbelt or not. Now, say a person tries to put through an image of a frog (random). How should I handle the image ...
0
votes
1answer
39 views

How to handle images that don’t pertain to image classifier at all?

I am trying to create a CNN model that classifies if a person is wearing a seatbelt or not to verify they drive safely. I know to get images of people wearing seatbelts and people not wearing ...
0
votes
0answers
29 views

How to choice CNN architecture for stitching images

I decided to start learning neural networks by creating a bot for the game. One of the intermediate steps is to create a global map from a series of inaccurate overlapping sub-maps. This task can be ...
0
votes
0answers
46 views

ConvNet - What to improve regarding architecture, procedure and technique?

I have a dataset of 180k images of license plates (so, not necessary to localize the license plate at first) for which I try to recognize the characters on the images (License plate recognition). All ...
0
votes
0answers
50 views

What are some scalable approaches to perform anomaly detection (for images with small cracks) with unsupervised learning?

I have some images with anomalies, like small cracks, but it's an imbalanced dataset. Please, suggest some effective scalable approaches. Should I consider convolutional auto-encoders? It's supposed ...
1
vote
0answers
45 views

Extending patch based image classification into image classification

I am trying to classify tampered, pristine images from set of images, in that I have built a network in which I would divide the image into multiple overlapping patches and then classify them into ...
0
votes
0answers
44 views

Non-trainable regularizer in loss function

I train a fully convoluted network for semantic segmentation. To each convolution blocks, I associate a module pruning feature maps to reduce the quantity of information generated by the network. From ...
2
votes
1answer
57 views

Can residual neural networks use other activation functions different from ReLU?

In many diagrams, as seen below, residual neural networks are only depicted with ReLU activation functions, but can residual NNs also use other activation functions, such as the sigmoid, hyperbolic ...
4
votes
0answers
62 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 ...
1
vote
0answers
35 views

How can one be sure that a particular neural network architecture would work?

Traditionally, when working with tabular data, one can be sure(or at least know) that a model works because the included features could explain a target variable, say "Price of a ticket" ...
1
vote
0answers
54 views

How can the FCNN reduce the dimensions of the input from $1048 \times 100$ to $523 \times 100$ with max-pooling?

I am trying to implement a paper on Image tempering detection and localization, the paper is Image Manipulation Detection and Localization Based on the Dual-Domain Convolutional Neural Networks, I was ...
0
votes
1answer
39 views

Is there a way to get landmark features automatically learned by a neural network?

Is there a way to get landmark features automatically learned by a neural network without having to manually pre-label them in the images that are being fed into the network?
0
votes
0answers
31 views

High mAP@50 with low precision and recall. What does it mean and what metric should be more important?

I am comparing models for the detection of objects for maritime Search and Rescue (SAR) purposes. From the models that I used, I got the best results for the improved version of YOLOv3 for small ...
1
vote
1answer
44 views

Why would the learning rate curve go backwards?

I'm working on recognizing the numbers 3 and 7 using the MNIST data set. I'm using cnn_learner() function from fastai library. When I plotted the learning rate, the ...
1
vote
0answers
37 views

Why does the number of channels in the PointNet increase as we go deeper?

For example, in PointNet, you see the 1D convolutions with the following channels 64 -> 128 -> 1024. Why not e.g. ...
0
votes
0answers
49 views

Need to determine a ML solution for the given graphical problem

I need to generate a 3D plane given a set of feature inputs. Most inputs are a range of values between 0 and 1 (sigmoidial), except a few. For example a rectangle: ...
1
vote
0answers
36 views

What is the amount of test data needed to evaluate a CNN?

I have an image dataset of about 400 images. 70% of these data points were used for training, 15% for validation, and 15% for testing. I am using the 70% to train a CNN-based binary classifier. I ...
1
vote
1answer
35 views

Do the order of the features ie channel matter for a 1d convolutional network?

Do the test dataset feature order and inference (real world) feature order have to be the same as the training dataset? For example, if features are in the order (a,c,b,e,d) for the training dataset, ...
0
votes
0answers
37 views

Where can I place an attention module for different computer vision tasks?

Where can I place an attention module for different computer vision tasks? For example, in this Github issue, the author is not sure where to place the attention module. Are there any rules or best ...
1
vote
0answers
40 views

Can text-independent writer identification be done without multi-sentence training datasets for each writer?

I am trying to learn more about text-independent writer identification and was hoping for some advice. I have a folder with 100k images, each of them with a different handwritten sentence. All of the ...
1
vote
1answer
42 views

Do I need to rotate the masks, if I also rotate the images and the masks are generated from the input?

I am training a neural network that takes an input (H, W, 3) and has the output of size (H', W', C). Now, to augment my dataset, ...
1
vote
1answer
43 views

How to quickly change hand-drawn shapes to symmetrical polished shapes?

Given a hand-drawn shape, I'd like to generate the corresponding symmetrical polished shapes such as circle, rectangle, triangle, trapezoid, square, parallelogram, etc. A short video demonstration ...
0
votes
0answers
20 views

Approaches for OCR building which can extract latex from the image as mathematical formulas

I have images of questions from the domain of mathematics, where the image can be a mixture of the English language and mathematical formulas. I want to build and train an OCR model like Harvard NLP's ...
2
votes
1answer
57 views

Why are RNNs used in some computer vision problems?

I am learning computer vision. When I was going through implementations of various computer vision projects, some OCR problems used GRU or LSTM, while some did not. I understand that RNNs are used ...
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 ...
3
votes
2answers
109 views

Is such a captcha AI-resistant?

Let's say we have a captcha system that consists of a greyscale picture (of a part of a street or something akin to re-captcha), divided into 9 blocks, with 2 missing pieces. You need to choose the ...
1
vote
1answer
42 views

How to prevent image recognition of my dataset with neural networks and make it hard to train them?

Suppose I have a private set of images containing some objects. How do i Make it very hard for the neural networks such as ImageNet to recognize these objects, while allowing humans to do it at the ...
1
vote
0answers
25 views

Suppress heatmap non-maxima in segmentation with UNet

I'm using U-Net for image segmentation. The model was trained with images that could contain up to 4 different classes. The train classes are never overlapping. The output of the UNet is a heatmap (...
0
votes
0answers
19 views

Indoor scene understanding dataset which can be used commercially?

Is there a (large) indoor scene understanding datasets (providing instance segmentation masks) which can be used commercially ? All large scene understanding datasets (SceneNet, ScanNet, InteriorNet, ....
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 ...
1
vote
0answers
28 views

How to measure/estimate the energy consumption of CNN models during testing?

Does someone know a method to estimate / measure the total energy consumption during the test phase of the well-known CNN models? So with a tool or a power meter... MIT has already a tool to estimate ...
1
vote
1answer
45 views

Can fully connected layers be used for feature detection?

I need help in understanding something basic. In this video, Andrew Ng says, essentially, that convolutional layers are better than fully connected (FC) layers because they use fewer parameters. But I'...
1
vote
0answers
56 views

When to use convolutional layers as opposed to fully connected layers?

I am still new to CNNs, but I would like to check my understanding between when to use convolutional layers versus fully connected layers. From what I have read, we can use convolutional layers with ...
1
vote
0answers
45 views

Atari Games: Pretrained CNN to accelerate training?

DQN for Atari takes considerable training time. For example, the 2015 paper in Nature notes that algorithms are trained for 50 million frames or equivalently around 38 days of game experience in total....
0
votes
1answer
28 views

How is it possible to get the output size of `n` Consecutive Convolutional layers? [closed]

Given network architecture, what are the possible ways to define fully connected layer fc1 to have a generalized structure such as ...
0
votes
0answers
35 views

DQN not learning the game Pong

Hello I'm trying to implement DQN Agent to play Atari-Pong game. But still after 500.000 parameter updates, the model still scores -21. This is my code, do you have any idea what could be wrong? ...
0
votes
0answers
23 views

CNN keras accuracy not improving

I am trying to duplicate and learn from example given on this website . With my little modification, I am trying to simple exchange color for example like red to orange in an image. The original ...
0
votes
0answers
19 views

Is there a 2D (sampled frequencies) music network in some kind of zoos like Imagenet to try it in order to get style transfer?

It looks like the music which is sampled and each sample has been transferred into frequency domain with FFT is in fact 2D object, capable to be dealed with CNN networks. So, it looks like if some ...
0
votes
0answers
25 views

Binary classification to recognize blobs on pictures generates many false-positive results

I am training a NN for blobs vs non-blobs recognition. Blobs example: Non-blobs: Keras architecture is: ...
1
vote
1answer
41 views

How will the input be preserved as we go deeper in CNN, where dimensions decrease drastically?

Our length of feature representation decreases as we go deeper into the CNN, I mean to say that horizontal and vertical lengths decrease while depth(channels) increase. So, how will the input be ...
0
votes
0answers
15 views

NN for defect detection

New to NN, I'm looking to get advice for the architectural implementation using tensorflow of a neural net for defect detection in the material as well as suggested image preprocessing to improve NN ...
0
votes
0answers
24 views

How much data do we need for making a successful de-noising auto-encoder?

Is there a guide how much data do you need for making successful denoising model using autoencoders? Or the rule is, the more data, the better it is? I tried with small dataset 350 samples, to see ...

1
2 3 4 5
16