Generalizing Cross Entropy Loss with a Beta Proper Composite Loss: An Improved Loss Function for Open Set Recognition
Open set recognition involves identifying data instances encountered during test time that do not belong to known classes in the training set. The majority of recent deep learning approaches to open set recognition use a cross entropy loss to train their networks. Surprisingly, other loss functions are seldom used. In our work, we explore generalizing cross entropy with a Beta loss. This Beta loss is a proper composite loss with a Beta weight function. This weight function adds the flexibility of putting more emphasis on different parts of the observation-conditioned class probability (i.e. $P(Y|X)$) range during training. We show that the flexibility gained through this is Beta loss function produces consistent improvements over cross entropy loss for open set recognition and produces state of the art results relative to recent methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Open Set LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards
We investigate the Multi-Armed Bandit problem with Temporally-Partitioned Rewards (TP-MAB) setting in this paper. In the TP-MAB setting, an agent will receive subsets of the reward over multiple rounds rather than the en…
Multi-Armed BanditsTemperature check: theory and practice for training models with softmax-cross-entropy losses
The softmax function combined with a cross-entropy loss is a principled approach to modeling probability distributions that has become ubiquitous in deep learning. The softmax function is defined by a lone hyperparameter…
Sentiment AnalysisReformulating van Rijsbergen's $F_β$ metric for weighted binary cross-entropy
The separation of performance metrics from gradient based loss functions may not always give optimal results and may miss vital aggregate information. This paper investigates incorporating a performance metric alongside …
A surrogate loss function for optimization of $F_β$ score in binary classification with imbalanced data
The $F_\beta$ score is a commonly used measure of classification performance, which plays crucial roles in classification tasks with imbalanced data sets. However, the $F_\beta$ score cannot be used as a loss function by…
Binary ClassificationClassificationGeneral ClassificationAligning Multiclass Neural Network Classifier Criterion with Task Performance via $F_β$-Score
Multiclass neural network classifiers are typically trained using cross-entropy loss. Following training, the performance of this same neural network is evaluated using an application-specific metric based on the multicl…
Binary Classification