# Rediscovering BCE Loss for Uniform Classification

arXiv: https://arxiv.org/abs/2403.07289 · HTML: https://mlsanity.com/paper/2403.07289/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Imbalanced Malware Images Classification: a CNN based Approach](https://mlsanity.com/paper/1708.08042/) (2017)

## Built on by (most cited first, 7 of 7)

- [SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures](https://mlsanity.com/paper/2503.01113/) (2025)
- [Towards Robust Infrared Small Target Detection: A Feature-Enhanced and Sensitivity-Tunable Framework](https://mlsanity.com/paper/2407.20090/) (2024)
- [Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation](https://mlsanity.com/paper/2408.12815/) (2024)
- [EPL: Empirical Prototype Learning for Deep Face Recognition](https://mlsanity.com/paper/2405.12447/) (2024)
- [Mapping Historic Urban Footprints in France: Balancing Quality, Scalability and AI Techniques](https://mlsanity.com/paper/2510.02097/) (2025)
- [Design and Development of an ML/DL Attack Resistance of RC-Based PUF for IoT Security](https://mlsanity.com/paper/2603.28798/) (2026)
- [SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation](https://mlsanity.com/paper/2605.14926/) (2026)

## Abstract (arXiv)

This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model's performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classification datasets and three feature extraction models show that, compared to the SoftMax loss, the models trained with the BCE loss not only exhibit higher uniform classification accuracy but also higher sample-wise classification accuracy. In addition, the learned bias from BCE loss is very close to the unified threshold used in the uniform classification. The features extracted by the models trained with BCE loss not only possess uniformity but also demonstrate better intra-class compactness and inter-class distinctiveness, yielding superior performance on open-set tasks such as face recognition.