Menu
I'm interested in taking advantage of some partially labeled data that I have in a deep learning task. I'm using a fully convolutional approach, not sampling patches from the labeled regions.
I have masks that outline regions of definite positive examples in an image, but the unmasked regions in the images are not necessarily negative - they may be positive. Does anyone know of a way to incorporate this type of class in a deep learning setting?
Triplet/contrastive loss seems like it may be the way to go, but I'm not sure how to accommodate the "fuzzy" or ambiguous negative/positive space.
210
Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost.
Deep learning neural networks are an example of an algorithm that natively supports multi-label classification problems. Neural network models for multi-label classification tasks can be easily defined and evaluated using the Keras deep learning library.
Earlier versions of neural networks such as the first perceptrons were shallow, composed of one input and one output layer, and at most one hidden layer in between. More than three layers (including input and output) qualifies as “deep” learning.
Deep learning is a subfield of machine learning, and neural networks make up the backbone of deep learning algorithms. In fact, it is the number of node layers, or depth, of neural networks that distinguishes a single neural network from a deep learning algorithm, which must have more than three.
Try label smoothing as described in section 7.5.1 of Deep Learning book:
We can assume that for some small constant
eps, the training set label y is correct with probability1 - eps, and otherwise any of the other possible labels might be correct.Label smoothing regularizes a model based on a softmax with
koutput values by replacing the hard 0 and 1 classification targets with targets ofeps / k and 1 - (k - 1) / k * eps, respectively.
See my question about implementing label smoothing in Pandas.
Otherwise if you know for sure, that some areas are negative, other are positive while some are uncertain, then you can introduce a third uncertain class. I have worked with data sets that contained uncertain class, which corresponded to samples that could belong to any of the available classes.
104
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
