New answers tagged

2

You should not use augmented data in the validation nor in the test set. Validation and test set are purely used for hyperparameter tuning and estimating the final performance, i.e. estimating the generalization error. These two data sets should be as close as possible to other data, which you could have acquired, but you actually haven not, i.e. your true ...


0

The threshold is typically chosen empirically, so there is no exact answer. It's dependent on how many corners you wish to select, and how strict you want the detection, which could depend on the use case, the dataset, and the block size of the algorithm. If you’re not sure what to choose for the threshold, I would suggest using a scheme relative to your ...


3

There are tasks in computer vision where recurrent neural networks (RNNs) can be useful because there's some sequential sub-task in the main task. For instance, in the paper Long-Term Recurrent Convolutional Networks for Visual Recognition and Description, the authors investigate the use of a neural network that is both recurrent and convolutional to solve ...


2

If the model is trained and held constant, then there are so-called adversarial attacks to modify images such that the model classifies them incorrectly (see Attacking Machine Learning with Adversarial Examples). However, if you want to make images that are untrainable, you are probably out of luck. Deep neural networks can learn to recognize even random ...


3

Yes it should be possible. You may have a bug in your code, or the wrong hyperparameters. Training ResNet-50 will take a long time. Try training on other sets of images and see what accuracy you get to check if your approach is correct. Or, try loading a pretrained model, and training from that.


1

You can do that pretty easily using Posenet or Openpose. Train the keypoints for Squats and then count it. :)


0

I ended up using a work around. I set up the network so that an C x C (i.e. 320 x 320) input would output a C x C mask for some constant C (in my case it was 320). I then resized the image I wanted to pass in to C x C, and then resized the output back to the original size of the Image.


0

Rules based on Gestalt psychology could be seen as a 'local minima' in terms of optimal image processing. Some of them could be surprisingly effective, but difficult to extend and improve upon, since they assume certain high level attributes that might not generalize well. "If it's circular, then it's a fruit 90% of the time" Modern methods like ...


1

Computer vision is a wide field, and besides the fact that deep learning dominates, there are still many, many other algorithms that see widespread use in both academia and industry. For tasks such as image classification / object recognition, the typical paradigm is some CNN architecture such as a ResNet or VGG. There has been lots of works to extend and ...


1

The ROIs in the input space are mapped to the feature map space, by dividing it by the net stride at that layer. Say, in a network, after a sequence of four 2x2 pooling layers, your image is reduced to 1/16 of the original size. (A 32*32 image is reduced to 2x2) So, the bounding boxes in the original space are mapped to the feature space by dividing by the ...


1

Your zero-classes just do not exist for the model. There is no information about them in training and test sets. I think the reason for overfitting is that your have very small size of the training set comparing to the number of parameters in your model. If it is easier for a model to remember all training entries - it will just do that. You need to prune ...


3

There are many computer vision (CV) algorithms and models that are used for different purposes. So, of course, I cannot list all of them, but I can enumerate some of them based on my experience and knowledge. Of course, this answer will only give you a flavor of the type of algorithm or model that you will find while solving CV tasks. For example, there are ...


2

(Of course, similar questions have been asked in the past and there are many sites, papers, video lessons, online that explain how CNNs work, but I think it's still a good idea to have a reference answer that hopefully will give you the main ideas behind CNNs.) A convolutional neural network (CNN) is a neural network that performs the convolution (or cross-...


2

Introduction Bag-of-features (BoF) (also known as bag-of-visual-words) is a method to represent the features of images (i.e. a feature extraction/generation/representation algorithm). BoF is inspired by the bag-of-words model often used in the context of NLP, hence the name. In the context of computer vision, BoF can be used for different purposes, such as ...


0

FCNs can and typically have downsampling operations. For example, u-net has downsampling (more precisely, max-pooling) operations. The difference between an FCN and a regular CNN is that the former does not have fully connected layers. See this answer for more info. Therefore, FCNs inherit the same properties of CNNs. There's nothing that a CNN (with fully ...


Top 50 recent answers are included