%0 Generic %1 kobs2020simloss %A Kobs, Konstantin %A Steininger, Michael %A Zehe, Albin %A Lautenschlager, Florian %A Hotho, Andreas %D 2020 %K author:zehe crossentropy lossfunction myown neuralnet %T SimLoss: Class Similarities in Cross Entropy %U http://arxiv.org/abs/2003.03182 %X One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.

@misc{kobs2020simloss, abstract = {One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.}, added-at = {2020-03-13T10:47:31.000+0100}, author = {Kobs, Konstantin and Steininger, Michael and Zehe, Albin and Lautenschlager, Florian and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/240b5051e8d4e5062a738652054accf41/albinzehe}, description = {[2003.03182] SimLoss: Class Similarities in Cross Entropy}, interhash = {c9693bde2183871e64852bd39bcf396b}, intrahash = {40b5051e8d4e5062a738652054accf41}, keywords = {author:zehe crossentropy lossfunction myown neuralnet}, note = {cite arxiv:2003.03182Comment: This paper is going to be published in the proceedings of the 25th International Symposium on Methodologies for Intelligent Systems (ISMIS)}, timestamp = {2023-10-11T10:29:52.000+0200}, title = {SimLoss: Class Similarities in Cross Entropy}, url = {http://arxiv.org/abs/2003.03182}, year = 2020 }