# Negative Log Likelihood Ratio Loss for Deep Neural Network Classification

arXiv: https://arxiv.org/abs/1804.10690 · HTML: https://mlsanity.com/paper/1804.10690/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2018.

## Built on by (most cited first, 17 of 17)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Cross-scale Multi-instance Learning for Pathological Image Diagnosis](https://mlsanity.com/paper/2304.00216/) (2023)
- [Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images](https://mlsanity.com/paper/2208.07322/) (2022)
- [Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities](https://mlsanity.com/paper/2312.08851/) (2023)
- [Intelligent Multi-View Test Time Augmentation](https://mlsanity.com/paper/2406.08593/) (2024)
- [DANCE: Deep Learning-Assisted Analysis of Protein Sequences Using Chaos Enhanced Kaleidoscopic Images](https://mlsanity.com/paper/2409.06694/) (2024)
- [Early prediction of the transferability of bovine embryos from videomicroscopy](https://mlsanity.com/paper/2501.07945/) (2025)
- [Sequence Analysis Using the Bezier Curve](https://mlsanity.com/paper/2503.14574/) (2025)
- [A Multi-Head Attention Soft Random Forest for Interpretable Patient No-Show Prediction](https://mlsanity.com/paper/2505.17344/) (2025)
- [CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions](https://mlsanity.com/paper/2603.01688/) (2026)
- [Deep Learning and Handheld Augmented Reality Based System for Optimal Data Collection in Fault Diagnostics Domain](https://mlsanity.com/paper/2206.07772/) (2022)
- [CQural: A Novel CNN based Hybrid Architecture for Quantum Continual Machine Learning](https://mlsanity.com/paper/2305.09738/) (2023)
- [Strong convexity-guided hyper-parameter optimization for flatter losses](https://mlsanity.com/paper/2402.05025/) (2024)
- [Automated Landfill Detection Using Deep Learning: A Comparative Study of Lightweight and Custom Architectures with the AerialWaste Dataset](https://mlsanity.com/paper/2508.18315/) (2025)
- [Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning](https://mlsanity.com/paper/2511.03616/) (2025)

## Abstract (arXiv)

In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from competing classes. We propose a discriminative loss function with negative log likelihood ratio between correct and competing classes. It significantly outperforms the cross-entropy loss on the CIFAR-10 image classification task.