# Learning to Predict Trustworthiness with Steep Slope Loss

arXiv: https://arxiv.org/abs/2110.00054 · HTML: https://mlsanity.com/paper/2110.00054/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [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)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [M2m: Imbalanced Classification via Major-to-minor Translation](https://mlsanity.com/paper/2004.00431/) (2020)
- [Confidence-Aware Learning for Deep Neural Networks](https://mlsanity.com/paper/2007.01458/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Functional Adversarial Attacks](https://mlsanity.com/paper/1906.00001/) (2019)
- [Metric-Free Individual Fairness in Online Learning](https://mlsanity.com/paper/2002.05474/) (2020)
- [G-softmax: Improving Intra-class Compactness and Inter-class Separability of Features](https://mlsanity.com/paper/1904.04317/) (2019)

## Built on by (most cited first, 11 of 11)

- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [Revisiting Confidence Estimation: Towards Reliable Failure Prediction](https://mlsanity.com/paper/2403.02886/) (2024)
- [Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers](https://mlsanity.com/paper/2406.18451/) (2024)
- [Improving the Reliability for Confidence Estimation](https://mlsanity.com/paper/2210.06776/) (2022)
- [Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors](https://mlsanity.com/paper/2410.02384/) (2024)
- [U-Trustworthy Models.Reliability, Competence, and Confidence in Decision-Making](https://mlsanity.com/paper/2401.02062/) (2024)
- [Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment](https://mlsanity.com/paper/2401.14628/) (2024)
- [Adaptive Confidence Regularization for Multimodal Failure Detection](https://mlsanity.com/paper/2603.02200/) (2026)
- [From Misclassifications to Outliers: Joint Reliability Assessment in Classification](https://mlsanity.com/paper/2603.03903/) (2026)
- [FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2609.04276/) (2026)

## Abstract (arXiv)

Understanding the trustworthiness of a prediction yielded by a classifier is critical for the safe and effective use of AI models. Prior efforts have been proven to be reliable on small-scale datasets. In this work, we study the problem of predicting trustworthiness on real-world large-scale datasets, where the task is more challenging due to high-dimensional features, diverse visual concepts, and large-scale samples. In such a setting, we observe that the trustworthiness predictors trained with prior-art loss functions, i.e., the cross entropy loss, focal loss, and true class probability confidence loss, are prone to view both correct predictions and incorrect predictions to be trustworthy. The reasons are two-fold. Firstly, correct predictions are generally dominant over incorrect predictions. Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets. To improve the generalizability of trustworthiness predictors, we propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other. The proposed loss is evaluated with two representative deep learning models, i.e., Vision Transformer and ResNet, as trustworthiness predictors. We conduct comprehensive experiments and analyses on ImageNet, which show that the proposed loss effectively improves the generalizability of trustworthiness predictors. The code and pre-trained trustworthiness predictors for reproducibility are available at https://github.com/luoyan407/predict_trustworthiness.