# Selective Prior Synchronization via SYNC Loss

arXiv: https://arxiv.org/abs/2602.11316 · HTML: https://mlsanity.com/paper/2602.11316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [What do we need to build explainable AI systems for the medical domain?](https://mlsanity.com/paper/1712.09923/) (2017)
- [Deep Gamblers: Learning to Abstain with Portfolio Theory](https://mlsanity.com/paper/1907.00208/) (2019)
- [Optimal strategies for reject option classifiers](https://mlsanity.com/paper/2101.12523/) (2021)
- [Classification with Rejection Based on Cost-sensitive Classification](https://mlsanity.com/paper/2010.11748/) (2020)
- [DOCTOR: A Simple Method for Detecting Misclassification Errors](https://mlsanity.com/paper/2106.02395/) (2021)
- [Learning to Reject with a Fixed Predictor: Application to Decontextualization](https://mlsanity.com/paper/2301.09044/) (2023)
- [Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data](https://mlsanity.com/paper/2207.07506/) (2022)
- [Towards Better Selective Classification](https://mlsanity.com/paper/2206.09034/) (2022)

## Abstract (arXiv)

Prediction under uncertainty is a critical requirement for the deep neural network to succeed responsibly. This paper focuses on selective prediction, which allows DNNs to make informed decisions about when to predict or abstain based on the uncertainty level of their predictions. Current methods are either ad-hoc such as SelectiveNet, focusing on how to modify the network architecture or objective function, or post-hoc such as softmax response, achieving selective prediction through analyzing the model's probabilistic outputs. We observe that post-hoc methods implicitly generate uncertainty information, termed the selective prior, which has traditionally been used only during inference. We argue that the selective prior provided by the selection mechanism is equally vital during the training stage. Therefore, we propose the SYNC loss which introduces a novel integration of ad-hoc and post-hoc method. Specifically, our approach incorporates the softmax response into the training process of SelectiveNet, enhancing its selective prediction capabilities by examining the selective prior. Evaluated across various datasets, including CIFAR-100, ImageNet-100, and Stanford Cars, our method not only enhances the model's generalization capabilities but also surpasses previous works in selective prediction performance, and sets new benchmarks for state-of-the-art performance.