# Gradient-based Novelty Detection Boosted by Self-supervised Binary Classification

arXiv: https://arxiv.org/abs/2112.09815 · HTML: https://mlsanity.com/paper/2112.09815/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 18 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Gradients as a Measure of Uncertainty in Neural Networks](https://mlsanity.com/paper/2008.08030/) (2020)
- [Novelty Detection Through Model-Based Characterization of Neural Networks](https://mlsanity.com/paper/2008.06094/) (2020)

## Built on by (most cited first, 10 of 10)

- [Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection](https://mlsanity.com/paper/2405.17816/) (2024)
- [Low-Dimensional Gradient Helps Out-of-Distribution Detection](https://mlsanity.com/paper/2310.17163/) (2023)
- [Exploring Transformers for Open-world Instance Segmentation](https://mlsanity.com/paper/2308.04206/) (2023)
- [Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection](https://mlsanity.com/paper/2209.07837/) (2022)
- [R2-AD2: Detecting Anomalies by Analysing the Raw Gradient](https://mlsanity.com/paper/2206.10259/) (2022)
- [GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection](https://mlsanity.com/paper/2505.16017/) (2025)
- [Hypercone Assisted Contour Generation for Out-of-Distribution Detection](https://mlsanity.com/paper/2501.10209/) (2025)
- [GROOD: GRadient-Aware Out-of-Distribution Detection](https://mlsanity.com/paper/2312.14427/) (2023)
- [Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection](https://mlsanity.com/paper/2510.12713/) (2025)
- [Disentangled Graph Prompting for Out-Of-Distribution Detection](https://mlsanity.com/paper/2603.29644/) (2026)

## Abstract (arXiv)

Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them. It is a critical step in data monitoring, behavior analysis and other applications, helping enable continual learning in the field. Conventional methods of OOD detection perform multi-variate analysis on an ensemble of data or features, and usually resort to the supervision with OOD data to improve the accuracy. In reality, such supervision is impractical as one cannot anticipate the anomalous data. In this paper, we propose a novel, self-supervised approach that does not rely on any pre-defined OOD data: (1) The new method evaluates the Mahalanobis distance of the gradients between the in-distribution and OOD data. (2) It is assisted by a self-supervised binary classifier to guide the label selection to generate the gradients, and maximize the Mahalanobis distance. In the evaluation with multiple datasets, such as CIFAR-10, CIFAR-100, SVHN and TinyImageNet, the proposed approach consistently outperforms state-of-the-art supervised and unsupervised methods in the area under the receiver operating characteristic (AUROC) and area under the precision-recall curve (AUPR) metrics. We further demonstrate that this detector is able to accurately learn one OOD class in continual learning.