People who code: we want your input. Take the Survey

Questions tagged [computer-vision]

Computer Vision is a subfield of computer science which deals with analyzing and understanding images. This includes detection of objects like faces in images or segmenting images.

Filter by
Sorted by
Tagged with
3
votes
1answer
169 views

Can I use fit() function with images in Keras?

I want to use vgg16 to train a dataset that contains images. Can I use fit() function instead of fit_generator() in Keras? How?...
1
vote
2answers
185 views

CNN, which layer to choose for a similarity measure

I built a model (InceptionResnet v2) to classify images and I would like to use it to measure similarity between objects. One way to measure that similarity is to catch an intermediate layer's ...
3
votes
1answer
134 views

Why does joint embedding of word and images work?

I often see some papers where the authors do point-wise multiplication of word and image embedding (e.g the image below). Why does this implementation works? I do not understand.
3
votes
1answer
231 views

How to label “other” while labeling image for object detection/classification?

I want to train a model to recognize the different categories of food e.g. rice, burger, apple, pizza, orange and other things. After the first training, I realized that the model is detecting other ...
1
vote
0answers
2k views

Converting video into frames using openCV

I am converting video into video-frames using the given code converting video into frames ...
1
vote
0answers
349 views

Adding layers in the middle of the deep learning model [closed]

I want to add new layers to a complex CNN model in Keras, how can I add a new layers in the middle of the sequential deep learning model?
1
vote
1answer
504 views

How to know if the deep learning model is overfitting or not?

I created a deep learning (CNN) model, I used data augmentation and two dropout layers (0.5). How to know if the deep learning model is overfitting or not?
1
vote
0answers
336 views

Performance of UNet on low resolution images

I read the U-Net paper yesterday and it talked mostly about how it uses a small dataset (<100) of high-resolution images and performs efficiently. I was wondering how it might perform on larger ...
6
votes
1answer
1k views

Implementing spatio-temporal convolutions in pytorch

I am trying to implement a layer to perform the (2+1)D convolutions described in this paper: https://arxiv.org/pdf/1711.11248.pdf The basic idea is as follows: Let's say I have a 3D convolutional ...
1
vote
0answers
76 views

Display tested batch and its predicted label in Keras

I am using Keras to create a deep learning model (CNN), how can I display all tested batch images and its predicted label?
2
votes
1answer
175 views

How to train convolutional neural networks on unbalanced datasets of images?

How can I train convolutional neural networks on unbalanced datasets of images? My dataset has around 400 classes and the classes have different number of images..
2
votes
1answer
1k views

Display images after augmentation in Keras

How can I display all images after augmentation? How can I get the number of the trained data after augmentation? Thank you
1
vote
0answers
48 views

Resources for CNN example with Keras

Please provide me with excellent resources to learn deep learning with Keras, imbalance images classes and using imageGenerator, Transfer learning with Keras. Thank you
2
votes
1answer
181 views

I do not understand the prediction result of the CNN model

I have used the following model: ...
2
votes
2answers
1k views

Data augmentation based on the class type in the CNN model

I would like to use CNN model to classify images but some classes in my dataset have low amount of data. Can I apply data augmentation based on the number of the images in the class? For example, ...
1
vote
0answers
77 views

CTC on GRID corpus

Can somebody help me in labeling GRID corpus dataset using CTC loss function? I am trying to implement it in tensorflow and being a beginner I am not getting any clue how to implement it, I know how ...
5
votes
1answer
1k views

Does image's background matter for detector training (CNN)?

Does an image's background matter for detector/localisation in the training part (using CNN)? For example, if I want to make a face detector, which one is better as training dataset? Faces cropped ...
1
vote
1answer
1k views

How to arrange the image dataset in CNN?

How do I arrange the image dataset in CNN? Should I put each image category in a separate folder? Or all of them in the same folder? Should the image name be the category name? I would like to see an ...
1
vote
0answers
3k views

Training Inception V3 based model using Keras with Tensorflow Backend

I am currently training a few custom models that require about 12Gb GPU memory at the most. My setup has about 96Gb of GPU memory and python/Jupyter still manages to hog up all the gpu memory to the ...
0
votes
1answer
54 views

Using cloud to create CNN model

Are there any differences in the results of training the deep learning algorithm (CNN) using a device with a GPU and using any device with a cloud service such as AWS and Floydhub?
0
votes
1answer
528 views

Perform Person Re-Identification on custom image set

I've been recently using the YOLO system to detect people on images, which turned out really well. My next step is to try to find images of the same person across the whole set of images I've ...
0
votes
1answer
547 views

The effect of the image type and the image conversion on deep learning CNN model

Does the type of the image affects (jpg, png, bmp) on the CNN deep learning algorithm? Dose converting the image type affects on the CNN deep learning algorithm (ex. converting bmp to jpg or ppm to ...
2
votes
0answers
284 views

Spatial Transformer Networks and Data Augmentation

We are all familiar with the famous Deep Mind paper STN. Upon implementation, such as here, did anyone still use input data augementation such as affine transformations? There are used to make CNN ...
1
vote
0answers
66 views

Vector Arithmetic using WGAN-GP (Wasserstein GANs with Gradient Penalty)

Vector arithmetic in the latent space has been demonstrated to produce meaningful output image samples from a trained DC-GAN in the paper by Chintala et al. In fact, the vector arithmetic they ...
0
votes
1answer
30 views

Computer Vision: Handling dataset(3D data or scan) with different timesteps

I'm planning on training a CNN on CT scans for classification. The problem is CT scans are taken slice by slice, and in a typical scan, there could be more than 200 slices. The number of slices in a ...
1
vote
0answers
80 views

Query about Landmark pooling layer in Fashionnet paper

I have gone through Deepfashion paper.I have query regarding Landmark pooling layer. 1) Image has 4,6 or 8 landmark points depending on cloth type. So how do you decide size of last FC layer in ...
2
votes
1answer
1k views

Classification of Colors using Machine Learning from an Array of Pixels

From a very high level of possible machine learning methodologies, what method of classification would be good to identify objects or situations based on the color sensor pixel array (i.e., 16x16 ...
4
votes
1answer
11k views

mAP scores on tensorboard (Tensorflow Object Detection API) are all 0 even though the loss value is low

I trained a faster-rcnn model on the tensorflow object detection API on a custom dataset. I found that the loss is ~2 after 3.5k steps. However, when I ran eval.py, the mAP scores are all almost 0 as ...
2
votes
1answer
166 views

How Do I Classify Dirty/Dusty Camera Images? [closed]

I would like to test (predict) whether camera images are dusty/dirty or not.; a classification task indeed. The question is about finding the most appropriate Machine Learning approach, perhaps any ...
2
votes
0answers
219 views

GTX 1080t ti rans out of memory

I have 60000 images divided into two classes. I have tried to build transfer learning with pretrained ResNet50 but my new GTX 1080 ti returns -1 after couples of epochs. My guess is that it runs out ...
2
votes
0answers
24 views

Given a query image Q and two other images X and Y, how to determine which one is most similar to Q?

Given a query image Q and two other images X and Y (you can assume they have more or less the same resolutions if that simplifies the problem), which algorithm would perform extremely well at ...
2
votes
1answer
141 views

Why don't convolutional computer vision networks use horizontally - symmetric filters?

If, for example, I have a neural network for classifying dog breeds, and I feed it an image of some dog, inherently it shouldn't matter whether I feed it the original image or the image, mirrored ...
2
votes
0answers
100 views

How to combine heterogeneous image features extracted with different algorithms for similar image retrieval?

Say I have access to several pre-trained CNNs (e.g. AlexNet, VGG, GoogleLeNet, ResNet, DenseNet, etc.) which I can use to extract features from an image by saving the activations of some hidden layer ...
3
votes
1answer
73 views

How do we predict what is in an image using unsupervised deep neural networks?

From my understanding of unsupervised DNNs for image classification: The input layer is a 4,096 dimension vector (for 64 x 64 images) The hidden layers represent much lower "features" as identified ...
11
votes
1answer
5k views

What is difference between Fully Connected layer and Bilinear layer in CNN?

What is the difference between Fully Connected layers and Bilinear layers in deep learning?
3
votes
1answer
2k views

How to convert night image to day image?

I have set of night images which I will be using for self driving. But I want to convert those images into day images. I have developed algorithm based on day image but it is not good for night images ...
0
votes
1answer
1k views

Detecting text region from an image

So I'm working on a document processing AI and I already have a character recognition model which performs decently well. Now the problem is, how do I feed each character to the model in order to make ...
6
votes
4answers
2k views

Why choose TensorFlow?

I have noticed that most of the deep learning developers use TensorFlow. So why choose TensorFlow? What is the advantage of TensorFlow over Theano and CNTK?
2
votes
3answers
904 views

The goal of fine tuning

I would like to ask what is the goal of fine-tuning a VGGNet on my dataset. What does fine-tuning mean? Does it mean to change the weights or keep the weight values?
2
votes
1answer
2k views

Using handcrafted features in CNN

What is the difference between using CNN with handcrafted features and CNN without handcrafted features? Thank you
12
votes
5answers
6k views

Unsupervised image segmentation

I am trying to implement an algorithm where given an image with several objects on a plane table, desired is the output of segmentation masks for each object. Unlike in CNN's, the objective here is to ...
2
votes
2answers
1k views

Watermark detection using Deep Learning [closed]

I have images with and without watermark. There is only one type of watermark. I have tried VGG16 transfer learning, but results were bad. What are the methods to ...
3
votes
0answers
44 views

Formula to calculate size of Capsule output similar to the formula for CNN?

Is there any formula to find the output dimensions of a capsule network similar to that of a Convolutional Neural Network? For Example: In CNN, we know that ...
1
vote
0answers
69 views

How to estimate Distance to Obstacles using Lidar's BEV(Bir's Eye view ) Representation?

I am using a implementation that use both camera and Lidar for 3D obstacle detection for self driving cars but I have no idea how to calculate the distance to the obstacles since the Lidar uses the ...
5
votes
1answer
760 views

Spatial Transformer Networks vs Deformable Convolutions

As I understand STN as described by the the deepmind paper https://arxiv.org/abs/1506.02025 allow a neural network to learn how to perform spatial transformations on the input image in order to ...
1
vote
1answer
83 views

What are the challenging benchmarks for self driving cars object detection beside Kitti

I am working on 3D object detection in the context of self driving cars and I was wondering if there are other challenging benchmarks for this beside Kitti.
8
votes
4answers
8k views

Exploratory Data Analysis with Image Datset

In Machine Learning Kernels on Kaggle I often see EDAs with structured data. So, I was wondering, if there are any recommended/standard procedures for EDA with image datasets. What kind of statistical ...
2
votes
1answer
48 views

Human Height Estimation using walking stride

Are there any papers or research showing a correlation between walking stride and human height? My purpose is to estimate height from walking stride of a person.
4
votes
4answers
3k views

Classification of very similar images

I have two groups of images, each one with 1000 samples. The speckle pattern, in this context, is the same as a random pattern or "white noise" image. So these images are fundamentally different. In ...
1
vote
1answer
87 views

Generative adversarial networks for multiple distribution noise removal

I am working on a project where I need to denoise images, and my dataset is composed of a big chunk of pairs ...

1
6 7
8
9 10