mlsanityData to 14 Oct 2026

Distributional Loss for Robust Classification

arXiv 2606.13223 ↗First posted 11 Jun 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution. This softer target formulation implicitly captures class ambiguity, mitigates overfitting, and encourages the learning of more robust decision boundaries, all without requiring additional label information. Experimental results demonstrate consistent improvements in robustness, with particularly pronounced gains in low-data regimes, while requiring only minimal modifications to standard training pipelines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

23 of 35 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Supervised Contrastive Learningcited by 2,829
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  5. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  6. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
  7. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  8. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  9. 2017A General and Adaptive Robust Loss Functioncited by 236
  10. 2020MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysiscited by 206
  11. 2016Robust Large Margin Deep Neural Networkscited by 118
  12. 2018Large Margin Deep Networks for Classificationcited by 112
11 more
  1. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  2. 2022PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functionscited by 63
  3. 2020Conditional Negative Sampling for Contrastive Learning of Visual Representationscited by 57
  4. 2018Improving Generalization via Scalable Neighborhood Component Analysiscited by 53
  5. 2023Loss Functions and Metrics in Deep Learningcited by 42
  6. 2019Deep Learning on Small Datasets without Pre-Training using Cosine Losscited by 41
  7. 2018Rethinking Feature Distribution for Loss Functions in Image Classificationcited by 39
  8. 2017OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learningcited by 37
  9. 2019Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimizationcited by 28
  10. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  11. 2026Nearest-Neighbor Density Estimation for Dependency Suppressioncited by 1

Built on by

Not cited yet.