Log In Sign Up

Revisiting lp-constrained Softmax Loss: A Comprehensive Study

by   Chintan Trivedi, et al.

Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited domain-specific classification tasks and not in a general fashion. Motivated by the lack of such a comprehensive study, in this paper we investigate the performance of lp-constrained softmax loss classifiers across different norm orders, magnitudes, and data dimensions in both proof-of-concept classification problems and real-world popular image classification tasks. Experimental results suggest collectively that lp-constrained softmax loss classifiers not only can achieve more accurate classification results but, at the same time, appear to be less prone to overfitting. The core findings hold across the three popular deep learning architectures tested and eight datasets examined, and suggest that lp normalization is a recommended data representation practice for image classification in terms of performance and convergence, and against overfitting.


Be Careful What You Backpropagate: A Case For Linear Output Activations & Gradient Boosting

In this work, we show that saturating output activation functions, such ...

Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image Classification

Deep learning models have gained remarkable performance on a variety of ...

Ensemble Soft-Margin Softmax Loss for Image Classification

Softmax loss is arguably one of the most popular losses to train CNN mod...

Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation

The softmax function is widely used in artificial neural networks for th...

Does Normalization Methods Play a Role for Hyperspectral Image Classification?

For Hyperspectral image (HSI) datasets, each class have their salient fe...

SSN: Learning Sparse Switchable Normalization via SparsestMax

Normalization methods improve both optimization and generalization of Co...