Questions tagged [computer-vision]

Questions related to image representation, segmentation, visual object categorization and image processing algorithms in general.

Filter by
Sorted by
Tagged with
43
votes
7answers
7k views

Neural network references (textbooks, online courses) for beginners

I want to learn Neural Networks. I am a Computational Linguist. I know statistical machine learning approaches and can code in Python. I am looking to start with its concepts, and know one or two ...
48
votes
4answers
41k views

What is translation invariance in computer vision and convolutional neural network?

I don't have computer vision background, yet when I read some image processing and convolutional neural networks related articles and papers, I constantly face the term, ...
12
votes
1answer
11k views

How to form a Precision-Recall curve when I only have one value for P-R?

I have a data mining assignment where I make a content-based image retrieval system. I have 20 images of 5 animals. So in total 100 images. My system returns the 10 most relevant images to an input ...
16
votes
3answers
14k views

hinge loss vs logistic loss advantages and disadvantages/limitations

Hinge loss can be defined using $\text{max}(0, 1-y_i\mathbf{w}^T\mathbf{x}_i)$ and the log loss can be defined as $\text{log}(1 + \exp(-y_i\mathbf{w}^T\mathbf{x}_i))$ I have the following questions: ...
12
votes
1answer
6k views

Fine Tuning vs Joint Training vs Feature Extraction

I am reading this paper http://zli115.web.engr.illinois.edu/wp-content/uploads/2016/10/0479.pdf It distinguishes between feature extraction and fine tuning in deep learning. I am not getting the ...
6
votes
3answers
4k views

use of t-test to compare performance of algorithms

I need a little bit guidance. I have to compare the classification performance of multiple algorithms using simple or paired t-test. Let's say I have four datasets (A,B,C) with training and test ...
5
votes
2answers
6k views

Difference between Mean/average accuracy and Overall accuracy

I just got confusion while reading the paper "Local Binary Pattern-Based Hyperspectral Image Classification With Superpixel Guidance". They mentioned that they repeated each experiment 10 times and ...
13
votes
2answers
6k views

Balancing Reconstruction vs KL Loss Variational Autoencoder

I am training a conditional variational autoencoder on a dataset of faces. When I set my KLL Loss equal to my Reconstruction loss term, my autoencoder seems unable to produce varied samples. I always ...
10
votes
2answers
5k views

Anchoring Faster RCNN

In the Faster RCNN paper when talking about anchoring, what do they mean by using "pyramids of reference boxes" and how is this done? Does this just mean that at each of the W*H*k anchor points a ...
10
votes
1answer
9k views

How to determine the number of convolutional operators in CNN?

In computer vision task, such as object classification, with Convolutional Neural Networks (CNN), the network provides an appealing performance. But I'm not sure how to set up the parameters in ...
11
votes
3answers
1k views

Convolutional Neural Network Scale Sensitivity

For the sake of example, lets suppose we're building an age estimator, based on the picture of a person. Below we have two people in suits, but the first one is clearly younger than the second one. (...
11
votes
1answer
3k views

Training a convolution neural network

I am currently working on a face recognition software that uses convolution neural networks to recognize faces. Based on my readings, I've gathered that a convolutional neural network has shared ...
3
votes
1answer
8k views

Fine Tuning vs. Transferlearning vs. Learning from scratch

In my master thesis, I am researching on transfer learning on a specific use Case, a traffic sign detector implemented as a Single Shot Detector with a VGG16 base network for classification. The ...
2
votes
1answer
38 views

Learning useful semantic representations of data

Training a neural network on its final task (e.g. classification) right from the beginning is not always the best way to go. I'd like to make a short list of recognized methods of motivating a NN to ...
6
votes
2answers
8k views

Simple way to cluster histograms

I'm trying to cluster set of histograms. The histograms represent the frequencies of the distribution for a numbers from 1 to 5. The following figure shows two samples of my data. I have 10,000 ...
1
vote
0answers
228 views

Bag of Features: why the distance between two histograms of the same image is different than 0?

I'm trying to implement a Content Based Image Retrieval application for small image datasets. I'm testing it just with 1 thousands images from Caltech1001. The approach that I'm using is the classic ...
1
vote
0answers
235 views

Finding objects in an image given a single instance of the object from the same image - Deep Learning approach

I have an aerial image containing planes like this: I want to detect planes in the image (find bounding boxes around planes). For this user draws a bounding box on one of the planes and the algorithm ...
0
votes
1answer
191 views

Can object detection be done by passing parts of images to an image classification network? [closed]

I am using a pre-trained image classification network. How is the object detection performace by passing the parts of the image individually to detect various objects. is there any other way to ...
0
votes
1answer
126 views

how does the addition of 1×1 layers reduce from the complexity and solve sparse structure in inception module?

Based on the (going deeper with convolutions) paper. The inception module consists of multiple branches, each branch consists of convolution layer and each layer has a different kernel size for ...
1
vote
1answer
1k views

Deep learning models for unsupervised semantic segmentation

I am working on semantic segmentation for satellite images using keras and python. It is my understanding that popular models like U-Net require mask images (labels). Are there any unsupervised deep ...
1
vote
2answers
2k views

How to normalize filters in convolutional neural networks?

Usually, when convolving images, the elements in the filter sum to one. Is this criterion enforced in convolutional neural networks? If yes, how?
1
vote
0answers
891 views

3d Convolution vs CNN-LSTM for Gesture recognition

I want to implement a gesture recognition system from video (of hand movements). Some people have experimented with 3d convolutions to extract not only spatial features out of images, but also ...
0
votes
1answer
269 views

How yolo9000 predicts big objects?

I have a theoretical question about Yolo9000. Since it's a fully convolutional neural network, I was wondering how can it predict large objects. To the best of my knowledge, each convolutional kernel "...
0
votes
0answers
6 views

In what situation many classification models (specialized) will be better to use instead of just 1 (generalist)?

Recently, I started working on Classification and Object detection. I am using a dev board to make ONLY inference. So I am just using the models created by someone else. As I have to develop a demo, ...
0
votes
1answer
401 views

liblinear one vs rest learn parameters

Liblinear (http://www.csie.ntu.edu.tw/~cjlin/liblinear/) does not support for probability estimates. Say I have three classes C1, C2 and C3. I want to learn the model paramters for each 'one vs rest' ...