I am working on a Person Re-Identification problem and am showing the results using a CMC curve.
I used augmented data/Image along with the normal images (Currently training on CUHK01) in the training set. While testing if I don't use the augmented data along with my normal test images for Calculating Rank let's say Rank_1 I get Rank_1 of ~30% on the other hand on using augmented data gives me a Rank_1 of ~65-70% (which is weirdly high regarding the current Rank_1 accuracy in the world).
So my questions are
a) How does augmented data affect the testing set especially in my case.
b) Am I over-fitting or something of that sort.
c) Is it a general rule to avoid usage of augmented images in the test case.
The reason behind using data augmentation is to reduce the chance of overfitting. This way you want to tell your model that the parameters (theta) are not correlated with the data that you are augmenting (alpha). That is achievable by augmenting each input by every possible alpha. But this is far from reality for a number of reasons, e.g. time/memory limitation, you might not be able to construct every possible augmentation, etc. so there might be some bias. Nevertheless, it still reduces the chance of overfitting to your dataset, but it might overfit to your augmentation.
Thus, if you have the augmentation, you might get more accuracy by matching to the augmented data due to the overfitting, which is an answer to question a. So I believe that the answer to the question b is yes.
In order to answer question c, I have not read about rules for data augmentation but in the literature of machine learning I presume that they avoid any augmentation on the test set. e.g. I quote from a paper
We augment the training images by
replacing the green screen with random background images, and
vary the appearance in terms of color and shading by intrinsic recoloring
Related
I dont mean that a neural network can complete the work of traditional image processing algorithm.What i want to say is if it exists a kind of neural network can use the parameters of the traditional method as input and outputs more universal parameters that dont require manual adjustment.Intuitively, my ideas are less efficient than using neural networks directly，but I don't know much about the mathematics of neural networks.
If I understood correctly, what you mean is for a traditional method (let's say thresholding), you want to find the best parameters using ann. It is possible but you have to supply so many training data which needs to be created, processed and evaluated that it will take a lot of time. AFAIK many mobile phones that have AI assisted camera use this method to find the best aperture, exposure..etc.
First of all, thank you very much. I still have two things to figure out. If I wanted to get a (or a set of) relatively optimal parameters, what data set would I need to build (such as some kind of error between input and output and threshold) ? Second, as you give an example, is it more efficient or better than traversal or Otsu to select the optimal threshold through neural networks in practice?To be honest, I wonder if this is really more efficient than training input and output directly using neural networks
For your second question, Otsu only works on cases where the histogram has two distinct peaks. Thresholding is a simple function but the cut-off value is based on your objective; there is no single "best" value valid for every case. So if you want to train a model for thresholding, I think you have to come up with separate models for each case (like a model for thresholding bright objects, another for darker ones...etc.) Maybe an additional output parameter for determining the aim works but I am not sure. Will it be more efficient and better? Depends on the case (and your definition of better). Otsu, traversal or adaptive thresholding does not work all the time (actually Otsu has very specific use cases). If they work for your case, excellent. If not, then things get messy. So to answer your question, it depends on your problem at hand.
For the first question, TBF, it is quite difficult to work with images in traditional ANNs. Images have a lot of pixels, so standard ANNs struggle with inputs. Moreover, when the location/scale of an object in the image changes, the whole pixel data changes even though the content is the same (These are the reasons why CNN's are superior to ANN's for images). For these reasons it is better to use processed metrics which contain condensed and location-invariant information. E.g. for thresholding, you can give the histogram and it returns a thresholding value. Therefore you need an ann with 256 input neurons (for an intensity histogram of 8bit grayscale image), 1 output neuron, and 1-2 middle layers with some deeply connected neurons (128 maybe?). Your training data will be a bunch of histograms as input and corresponding best threshold value for each histogram. Then once training is finished, you can give the ANN a histogram it has never seen before and it will tell you the optimal thresholding value based on its training.
what I want to do is a model that can output different parameters (parameter sets) based on different input images, so I think if you choose a good enough data set it should be somewhat universal.
Most likely, but your data set should be quite inclusive of expected images (in terms of metrics and features), which means it has to be large.
Also, I don't know much about modeling -- can I use a function about the output/parameters (which might be a function about the result of the traditional method) as an error in the back-propagation by create a custom loss function?
I think so, but training the model will be more involved than using predefined loss functions because, well, you have to write them. Also you have to test they work as expected.
It is common practice to augment data (add samples programmatically, such as random crops, etc. in the case of a dataset consisting of images) on both training and test set, or just the training data set?
Only on training. Data augmentation is used to increase the size of the training set and to get more different images.
Technically, you could use data augmentation on the test set to see how the model behaves on such images, but usually, people don't do it.
Data augmentation is done only on training set as it helps the model become more generalize and robust. So there's no point of augmenting the test set.
This answer on stats.SE makes the case for applying crops on the validation / test sets so as to make that input similar the the input in the training set that the network was trained on.
Do it only on the training set. And, of course, make sure that the augmentation does not make the label wrong (e.g. when rotating 6 and 9 by about 180°).
The reason why we use a training and a test set in the first place is that we want to estimate the error our system will have in reality. So the data for the test set should be as close to real data as possible.
If you do it on the test set, you might have the problem that you introduce errors. For example, say you want to recognize digits and you augment by rotating. Then a 6 might look like a 9. But not all examples are that easy. Better be save than sorry.
I would argue that, in some cases, using data augmentation for the validation set can be helpful.
For example, I train a lot of CNNs for medical image segmentation. Many of the augmentation transforms that I use are meant to reduce the image quality so that the network is trained to be robust against such data. If the training set looks bad and the validation set looks nice, it will be hard to compare the losses during training and therefore assessing overfit will be complicated.
I would never use augmentation for the test set unless I'm using test-time augmentation to improve results or estimate aleatoric uncertainty.
In computer vision, you can use data augmentation during test time to obtain different views on the test image. You then have to aggregate the results obtained from each image for example by averaging them.
For example, given this symbol below, changing the point of view can lead to different interpretations :
Some image preprocessing software tools like Roboflow (https://roboflow.com/) apply data augmentation to test data as well. I'd say that if one is dealing with small and rare objects, say, cerebral microbleeds (which are tiny and difficult to spot on magnetic resonance images), augmenting one's test set could be useful. Then you can verify that your model has learned to detect these objects given different orientation and brightness conditions (given that your training data has been augmented in the same way).
The goal of data augmentation is to generalize the model and make it learn more orientation of the images, such that the during testing the model is able to apprehend the test data well. So, it is well practiced to use augmentation technique only for training sets.
The point of adding validation data is to build generalized model so it is nothing but to predict real-world data. inorder to predict real-world data, the validation set should contain real data. There is no problem with augmenting validation data but it won't increase the accuracy of the model.
Here are my two cents:
You train your model on the training data and the validation data: the former to optimize your parameters, and the latter to give you an appropriate stopping condition. The test data is to give you a real-world estimate of how well you can expect your model to perform.
For training, you can augment your training data to increase robustness to various factors including, but not limited to, sampling error, bias between data sources, shifts in global data distribution, positioning, and any other sort of variation you would like to account for.
The validation data should indicate to the training method when the model is most generalizable. By this logic, if you expect to see some variation in real-world data that can be simulated using data augmentation, then by all means, the validation dataset should be augmented.
The test data, on the other hand, should not be augmented, except potentially in special scenarios where data is very limited, and an estimate of real-world performance on test data has too much variance.
You can use augmentation data in training, validation and test sets.
The only thing to avoid is using the same data from the training set in validation or test sets.
For example, if you generate 3 augmented instances from an register of the training data, make sure that no one of these 3 augmented instances accidentally ends up in the validation or test sets.
It turns out that using data from the training set, even augmented data, to validate or test a model is a methodology mistake.
I am working on Soil Spectral Classification using neural networks and I have data from my Professor obtained from his lab which consists of spectral reflectance from wavelength 1200 nm to 2400 nm. He only has 270 samples.
I have been unable to train the network for accuracy more than 74% since the training data is very less (only 270 samples). I was concerned that my Matlab code is not correct, but when I used the Neural Net Toolbox in Matlab, I got the same results...nothing more than 75% accuracy.
When I talked to my Professor about it, he said that he does not have any more data, but asked me to do random perturbation on this data to obtain more data. I have research online about random perturbation of data, but have come up short.
Can someone point me in the right direction for performing random perturbation on 270 samples of data so that I can get more data?
Also, since by doing this, I will be constructing 'fake' data, I don't see how the neural network would be any better cos isn't the point of neural nets using actual real valid data to train the network?
Thanks,
Faisal.
I think trying to fabricate more data is a bad idea: you can't create anything with higher information content than you already have, unless you know the true distribution of the data to sample from. If you did, however, you'd be able to classify with the Bayes optimal error rate, which would be impossible to beat.
What I'd be looking at instead is whether you can alter the parameters of your neural net to improve performance. The thing that immediately springs to mind with small amounts of training data is your weight regulariser (are you even using regularised weights), which can be seen as a prior on the weights if you're that way inclined. I'd also look at altering the activation functions if you're using simple linear activations, and the number of hidden nodes in addition (with so few examples, I'd use very few, or even bypass the hidden layer entirely since it's hard to learn nonlinear interactions with limited data).
While I'd not normally recommend it, you should probably use cross-validation to set these hyper-parameters given the limited size, as you're going to get unhelpful insight from a 10-20% test set size. You might hold out 10-20% for final testing, however, so as to not bias the results in your favour.
First, some general advice:
Normalize each input and output variable to [0.0, 1.0]
When using a feedforward MLP, try to use 2 or more hidden layers
Make sure your number of neurons per hidden layer is big enough, so the network is able to tackle the complexity of your data
It should always be possible to get to 100% accuracy on a training set if the complexity of your model is sufficient. But be careful, 100% training set accuracy does not necessarily mean that your model does perform well on unseen data (generalization performance).
Random perturbation of your data can improve generalization performance, if the perturbation you are adding occurs in practice (or at least similar perturbation). This works because this means teaching your network on how the data could look different but still belong to the given labels.
In the case of image classification, you could rotate, scale, noise, etc. the input image (the output stays the same, naturally). You will need to figure out what kind of perturbation could apply to your data. For some problems this is difficult or does not yield any improvement, so you need to try it out. If this does not work, it does not necessarily mean your implementation or data are broken.
The easiest way to add random noise to your data would be to apply gaussian noise.
I suppose your measures have errors associated with them (a measure without errors has almost no meaning). For each measured value M+-DeltaM you can generate a new number with N(M,DeltaM), where n is the normal distribution.
This will add new points as experimental noise from previous ones, and will add help take into account exprimental errors in the measures for the classification. I'm not sure however if it's possible to know in advance how helpful this will be !
I am wondering how can I claim that I correctly catch the "noise" in my data ?
To be more specific, take Principle Component Analysis as example, we know that in PCA, after doing SVD, we can zeros out the small singular values and reconstruct the original matrix using low-rank approximation.
Then can I claim what's been ignored is indeed noise in the data ?
Is there any evaluation metric for this ?
The only method I can come up with is simply subtract the original data from the reconstructed data.
Then, try to fit a Gaussian over it, seeing if the fitness is good.
Is that conventional method in field like DSP ??
BTW, I think in typical machine learning tasks, the measurement would be the follow up classification performance, but since I am doing purely generative model, there are no labels attached.
The way I see it, the definition of noise would depend on the domain of the problem. Therefore the strategy for reducing it would be different on each domain.
For instance, having a noisy signal in problems like seismic formation classification or a noisy image on a face classification problem would be drastically different to the noise produced by improperly tagged data in a medical diagnostic problem or the noise because similar words with different meaning in a language classification problem for documents.
When the noise is because of a given (or a set of) data point, then the solution is as simple as ignore those data points (although identify those data points most of the time is the challenging part)
From your example I guess you are more concerning about the case when the noise is embedded into the features (like in the seismic example). Sometimes people tend to pre-process the data with a noise reduction filter like the median filter (http://en.wikipedia.org/wiki/Median_filter). In contrast, some other people tend to reduce the dimension of the data to reduce noise, and PCA is used in this scenario.
Both strategies are valid, and normally people try both and cross-validate them to see which one gave better results.
What you did is a good metric to check gaussian noise. However, for non-gaussian noise your metric can give you false negatives (bad fitness but still good noise reduction)
Personally, if you want to prove the efficacy of the noise reduction, I'd use a task-based evaluation. I assume you're doing this for some purpose, to solve some problem? If so, solve the task with the original noisy matrix and the new clean one. If the latter works better, what was discarded was noise, for the purposes of the task you're interested in. I think some objective measure of noise is pretty hard to define.
I have found this. it is very resoureful, needs good time to understand.
https://sci2s.ugr.es/noisydata#Introduction%20to%20Noise%20in%20Data%20Mining
How should I approach a situtation when I try to apply some ML algorithm (classification, to be more specific, SVM in particular) over some high dimensional input, and the results I get are not quite satisfactory?
1, 2 or 3 dimensional data can be visualized, along with the algorithm's results, so you can get the hang of what's going on, and have some idea how to aproach the problem. Once the data is over 3 dimensions, other than intuitively playing around with the parameters I am not really sure how to attack it?
What do you do to the data? My answer: nothing. SVMs are designed to handle high-dimensional data. I'm working on a research problem right now that involves supervised classification using SVMs. Along with finding sources on the Internet, I did my own experiments on the impact of dimensionality reduction prior to classification. Preprocessing the features using PCA/LDA did not significantly increase classification accuracy of the SVM.
To me, this totally makes sense from the way SVMs work. Let x be an m-dimensional feature vector. Let y = Ax where y is in R^n and x is in R^m for n < m, i.e., y is x projected onto a space of lower dimension. If the classes Y1 and Y2 are linearly separable in R^n, then the corresponding classes X1 and X2 are linearly separable in R^m. Therefore, the original subspaces should be "at least" as separable as their projections onto lower dimensions, i.e., PCA should not help, in theory.
Here is one discussion that debates the use of PCA before SVM: link
What you can do is change your SVM parameters. For example, with libsvm link, the parameters C and gamma are crucially important to classification success. The libsvm faq, particularly this entry link, contains more helpful tips. Among them:
Scale your features before classification.
Try to obtain balanced classes. If impossible, then penalize one class more than the other. See more references on SVM imbalance.
Check the SVM parameters. Try many combinations to arrive at the best one.
Use the RBF kernel first. It almost always works best (computationally speaking).
Almost forgot... before testing, cross validate!
EDIT: Let me just add this "data point." I recently did another large-scale experiment using the SVM with PCA preprocessing on four exclusive data sets. PCA did not improve the classification results for any choice of reduced dimensionality. The original data with simple diagonal scaling (for each feature, subtract mean and divide by standard deviation) performed better. I'm not making any broad conclusion -- just sharing this one experiment. Maybe on different data, PCA can help.
Some suggestions:
Project data (just for visualization) to a lower-dimensional space (using PCA or MDS or whatever makes sense for your data)
Try to understand why learning fails. Do you think it overfits? Do you think you have enough data? Is it possible there isn't enough information in your features to solve the task you are trying to solve? There are ways to answer each of these questions without visualizing the data.
Also, if you tell us what the task is and what your SVM output is, there may be more specific suggestions people could make.
You can try reducing the dimensionality of the problem by PCA or the similar technique. Beware that PCA has two important points. (1) It assumes that the data it is applied to is normally distributed and (2) the resulting data looses its natural meaning (resulting in a blackbox). If you can live with that, try it.
Another option is to try several parameter selection algorithms. Since SVM's were already mentioned here, you might try the approach of Chang and Li (Feature Ranking Using Linear SVM) in which they used linear SVM to pre-select "interesting features" and then used RBF - based SVM on the selected features. If you are familiar with Orange, a python data mining library, you will be able to code this method in less than an hour. Note that this is a greedy approach which, due to its "greediness" might fail in cases where the input variables are highly correlated. In that case, and if you cannot solve this problem with PCA (see above), you might want to go to heuristic methods, which try to select best possible combinations of predictors. The main pitfall of this kind of approaches is the high potential of overfitting. Make sure you have a bunch "virgin" data that was not seen during the entire process of model building. Test your model on that data only once, after you are sure that the model is ready. If you fail, don't use this data once more to validate another model, you will have to find a new data set. Otherwise you won't be sure that you didn't overfit once more.
List of selected papers on parameter selection:
Feature selection for high-dimensional genomic microarray data
Oh, and one more thing about SVM. SVM is a black box. You better figure out what is the mechanism that generate the data and model the mechanism and not the data. On the other hand, if this would be possible, most probably you wouldn't be here asking this question (and I wouldn't be so bitter about overfitting).
List of selected papers on parameter selection
Feature selection for high-dimensional genomic microarray data
Wrappers for feature subset selection
Parameter selection in particle swarm optimization
I worked in the laboratory that developed this Stochastic method to determine, in silico, the drug like character of molecules
I would approach the problem as follows:
What do you mean by "the results I get are not quite satisfactory"?
If the classification rate on the training data is unsatisfactory, it implies that either
You have outliers in your training data (data that is misclassified). In this case you can try algorithms such as RANSAC to deal with it.
Your model(SVM in this case) is not well suited for this problem. This can be diagnozed by trying other models (adaboost etc.) or adding more parameters to your current model.
The representation of the data is not well suited for your classification task. In this case preprocessing the data with feature selection or dimensionality reduction techniques would help
If the classification rate on the test data is unsatisfactory, it implies that your model overfits the data:
Either your model is too complex(too many parameters) and it needs to be constrained further,
Or you trained it on a training set which is too small and you need more data
Of course it may be a mixture of the above elements. These are all "blind" methods to attack the problem. In order to gain more insight into the problem you may use visualization methods by projecting the data into lower dimensions or look for models which are suited better to the problem domain as you understand it (for example if you know the data is normally distributed you can use GMMs to model the data ...)
If I'm not wrong, you are trying to see which parameters to the SVM gives you the best result. Your problem is model/curve fitting.
I worked on a similar problem couple of years ago. There are tons of libraries and algos to do the same. I used Newton-Raphson's algorithm and a variation of genetic algorithm to fit the curve.
Generate/guess/get the result you are hoping for, through real world experiment (or if you are doing simple classification, just do it yourself). Compare this with the output of your SVM. The algos I mentioned earlier reiterates this process till the result of your model(SVM in this case) somewhat matches the expected values (note that this process would take some time based your problem/data size.. it took about 2 months for me on a 140 node beowulf cluster).
If you choose to go with Newton-Raphson's, this might be a good place to start.